A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API
This report summarizes scanner evidence for anthropics/claude-quickstarts, a TypeScript project with 17,864 GitHub stars. SynthScan examined 109,978 lines of code across 539 source files, recording 491 pattern matches distributed across 17 syntactic categories. The legacy adjusted pattern signal is 6.3 (Moderate pattern signal); it is not an authorship estimate.
Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.
Use each vector to guide manual verification of the underlying findings.
Can maintainers explain intent, assumptions, and trade-offs? 362 finding(s).
Are imports declared and package/API names verified? 55 finding(s).
Are wrappers, guards, and repeated structures necessary? 306 finding(s).
Which changes need focused human review? 491 finding(s).
This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.
Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.
This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.
The scanner identified 491 distinct pattern matches across 17 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.
Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | autonomous-coding/test_security.py | 115 | def test_validate_init_script(): | CODE |
| LOW | autonomous-coding/security.py | 279 | def get_command_for_validation(cmd: str, segments: list[str]) -> str: | CODE |
| LOW | agents/test_message_params.py | 173 | def test_invalid_metadata_field(self) -> None: | CODE |
| LOW | financial-data-analyst/components/ui/chart.tsx | 325 | function getPayloadConfigFromPayload( | CODE |
| LOW | computer-use-demo/computer_use_demo/streamlit.py | 468 | def maybe_add_interruption_blocks(): | CODE |
| LOW | computer-use-demo/computer_use_demo/loop.py | 244 | def _maybe_filter_to_n_most_recent_images( | CODE |
| LOW | computer-use-demo/computer_use_demo/loop.py | 385 | def _maybe_prepend_system_tool_result(result: ToolResult, result_text: str): | CODE |
| LOW | computer-use-demo/computer_use_demo/tools/computer.py | 220 | def validate_and_get_coordinates(self, coordinate: tuple[int, int] | None = None): | CODE |
| LOW | computer-use-demo/tests/streamlit_test.py | 49 | def test_thinking_modes_follow_selected_model( | CODE |
| LOW | computer-use-demo/tests/streamlit_test.py | 61 | def test_interruption_blocks_keep_toolset_name(): | CODE |
| LOW | computer-use-demo/tests/loop_test.py | 84 | async def _run_loop_and_get_request_kwargs(**loop_kwargs): | CODE |
| LOW⚡ | computer-use-demo/tests/loop_test.py | 116 | async def test_loop_thinking_off_sends_no_thinking_params(): | CODE |
| LOW⚡ | computer-use-demo/tests/loop_test.py | 121 | async def test_loop_adaptive_thinking_sends_effort(): | CODE |
| LOW⚡ | computer-use-demo/tests/loop_test.py | 131 | async def test_loop_extended_thinking_sends_budget(): | CODE |
| LOW⚡ | computer-use-demo/tests/loop_test.py | 140 | async def test_loop_toolset_sends_no_beta_header_without_flags(): | CODE |
| LOW⚡ | computer-use-demo/tests/loop_test.py | 149 | async def test_loop_toolset_on_anthropic_keeps_prompt_caching_beta(): | CODE |
| LOW⚡ | computer-use-demo/tests/loop_test.py | 156 | async def test_loop_toolset_member_calls_run_sequentially_and_stop_on_failure(): | CODE |
| LOW⚡ | computer-use-demo/tests/tools/computer_test.py | 132 | async def test_computer_tool_invalid_action(computer_tool): | CODE |
| LOW⚡ | computer-use-demo/tests/tools/computer_test.py | 138 | async def test_computer_tool_missing_coordinate(computer_tool): | CODE |
| LOW⚡ | computer-use-demo/tests/tools/computer_test.py | 144 | async def test_computer_tool_missing_text(computer_tool): | CODE |
| LOW⚡ | computer-use-demo/tests/tools/computer_test.py | 154 | def test_computer_toolset_to_params_is_a_nameless_entry(computer_toolset): | CODE |
| LOW⚡ | computer-use-demo/tests/tools/computer_test.py | 159 | async def test_computer_toolset_key_repeat(computer_toolset): | CODE |
| LOW⚡ | computer-use-demo/tests/tools/computer_test.py | 169 | async def test_computer_toolset_key_repeat_quotes_each_key(computer_toolset): | CODE |
| LOW⚡ | computer-use-demo/tests/tools/computer_test.py | 179 | async def test_computer_toolset_key_without_repeat_takes_the_quoted_path( | CODE |
| LOW⚡ | computer-use-demo/tests/tools/computer_test.py | 191 | async def test_computer_toolset_key_rejects_coordinate(computer_toolset): | CODE |
| LOW⚡ | computer-use-demo/tests/tools/computer_test.py | 197 | async def test_computer_toolset_key_repeat_out_of_bounds(computer_toolset): | CODE |
| LOW⚡ | computer-use-demo/tests/tools/computer_test.py | 203 | async def test_computer_toolset_click_accepts_text_modifier(computer_toolset): | CODE |
| LOW | computer-use-demo/tests/tools/computer_test.py | 26 | async def test_computer_tool_mouse_move(computer_tool): | CODE |
| LOW | computer-use-demo/tests/tools/computer_test.py | 54 | async def test_computer_tool_screenshot(computer_tool): | CODE |
| LOW | computer-use-demo/tests/tools/computer_test.py | 65 | async def test_computer_tool_scaling(computer_tool): | CODE |
| LOW | computer-use-demo/tests/tools/computer_test.py | 88 | async def test_computer_tool_scaling_with_different_aspect_ratio(computer_tool): | CODE |
| LOW | computer-use-demo/tests/tools/computer_test.py | 105 | async def test_computer_tool_no_scaling_for_unsupported_resolution(computer_tool): | CODE |
| LOW | computer-use-demo/tests/tools/computer_test.py | 121 | async def test_computer_tool_scaling_out_of_bounds(computer_tool): | CODE |
| LOW | computer-use-demo/tests/tools/computer_test.py | 214 | async def test_computer_toolset_drag_accepts_text_modifier(computer_toolset): | CODE |
| LOW | computer-use-demo/tests/tools/computer_test.py | 229 | async def test_computer_toolset_invalid_member(computer_toolset): | CODE |
| LOW | computer-use-demo/tests/tools/computer_test.py | 235 | async def test_tool_collection_routes_member_calls(computer_toolset): | CODE |
| LOW | computer-use-demo/tests/tools/computer_test.py | 277 | async def test_zoom_crops_the_physical_capture_and_fits_the_screenshot_frame( | CODE |
| LOW | computer-use-demo/tests/tools/computer_test.py | 295 | async def test_zoom_without_scaling_uses_screenshot_pixels_directly(zoom_capture): | CODE |
| LOW | computer-use-demo/tests/tools/computer_test.py | 306 | async def test_zoom_is_a_toolset_member(zoom_capture, computer_toolset): | CODE |
| LOW | computer-use-demo/tests/tools/computer_test.py | 325 | async def test_zoom_rejects_malformed_regions(zoom_capture, region, message): | CODE |
| LOW⚡ | computer-use-demo/tests/tools/bash_test.py | 22 | async def test_bash_tool_run_command(bash_tool): | CODE |
| LOW⚡ | computer-use-demo/tests/tools/bash_test.py | 29 | async def test_bash_tool_no_command(bash_tool): | CODE |
| LOW⚡ | computer-use-demo/tests/tools/bash_test.py | 35 | async def test_bash_tool_session_creation(bash_tool): | CODE |
| LOW⚡ | computer-use-demo/tests/tools/bash_test.py | 42 | async def test_bash_tool_session_reuse(bash_tool): | CODE |
| LOW⚡ | computer-use-demo/tests/tools/bash_test.py | 51 | async def test_bash_tool_session_error(bash_tool): | CODE |
| LOW⚡ | computer-use-demo/tests/tools/bash_test.py | 57 | async def test_bash_tool_non_zero_exit(bash_tool): | CODE |
| LOW | …s/assistant-ui/lib/managed-agents/runtime-provider.tsx | 133 | export function ManagedAgentsRuntimeProvider({ children }: { children: React.ReactNode }) { | CODE |
| LOW | managed-agents/linear/src/managed-agents-webhook.ts | 31 | export async function handleManagedAgentsWebhook(req: Request): Promise<Response> { | CODE |
| LOW | managed-agents/slack/src/managed-agents-webhook.ts | 24 | export async function handleManagedAgentsWebhook(req: Request): Promise<Response> { | CODE |
| LOW⚡ | computer-use-best-practices/tests/test_zoom.py | 5 | def test_zoom_in_computer_schema() -> None: | CODE |
| LOW⚡ | computer-use-best-practices/tests/test_zoom.py | 12 | def test_zoom_in_browser_schema() -> None: | CODE |
| LOW⚡ | computer-use-best-practices/tests/test_zoom.py | 18 | def test_computer_zoom_validation() -> None: | CODE |
| LOW | computer-use-best-practices/tests/test_result.py | 4 | def test_errored_result_replaces_image_with_placeholder(): | CODE |
| LOW | computer-use-best-practices/tests/test_result.py | 13 | def test_ok_result_emits_image(): | CODE |
| LOW⚡ | computer-use-best-practices/tests/test_build_tools.py | 19 | def test_default_includes_both_sets(monkeypatch: pytest.MonkeyPatch) -> None: | CODE |
| LOW⚡ | computer-use-best-practices/tests/test_build_tools.py | 26 | def test_disable_computer_only(monkeypatch: pytest.MonkeyPatch) -> None: | CODE |
| LOW⚡ | computer-use-best-practices/tests/test_build_tools.py | 36 | def test_disable_browser_only(monkeypatch: pytest.MonkeyPatch) -> None: | CODE |
| LOW⚡ | computer-use-best-practices/tests/test_build_tools.py | 44 | def test_both_disabled_raises(monkeypatch: pytest.MonkeyPatch) -> None: | CODE |
| LOW⚡ | computer-use-best-practices/tests/test_computer.py | 42 | def test_type_text_uses_unicode_not_keycodes(captured): | CODE |
| LOW⚡ | computer-use-best-practices/tests/test_computer.py | 52 | def test_type_text_sends_real_keys_for_control_chars(captured): | CODE |
| 171 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | autonomous-coding/test_security.py | 52 | ("npm install && npm run build", ["npm", "npm"]), | CODE |
| HIGH | autonomous-coding/test_security.py | 56 | ("git status || git init", ["git", "git"]), | CODE |
| HIGH | autonomous-coding/test_security.py | 253 | "npm install && npm run build", | CODE |
| HIGH | autonomous-coding/agent.py | 202 | print(" npm install && npm run dev") | CODE |
| HIGH⚡ | browser-toolset/python/cdp_browser.py | 270 | const name = (el) => (el.getAttribute('aria-label') || el.innerText || el.value || el.placeholder || '') | CODE |
| HIGH⚡ | browser-toolset/python/cdp_browser.py | 276 | if (rect.width === 0 && rect.height === 0) continue; // not rendered | CODE |
| HIGH⚡ | browser-toolset/python/cdp_browser.py | 280 | lines.push(`- ${role} "${name(el)}" [${ref}]`); | CODE |
| HIGH⚡ | browser-toolset/python/cdp_browser.py | 287 | const el = window.__cdpBrowserRefs && window.__cdpBrowserRefs.byRef.get(ref); | CODE |
| HIGH⚡ | browser-toolset/python/cdp_browser.py | 288 | if (!el || !el.isConnected) return null; | CODE |
| HIGH | …naged-agents/self-hosted-sandboxes/archil/sandboxes.py | 23 | apt-get update -qq && apt-get install -y -qq --no-install-recommends ca-certificates curl git ripgrep unzip sqlite3 >/de | CODE |
| HIGH | managed-agents/self-hosted-sandboxes/archil/on-work.py | 58 | f"mkdir -p /mnt/edgar && archil -q mount {disk} /mnt/edgar --region {region} --shared >/dev/null" | CODE |
| HIGH | managed-agents/self-hosted-sandboxes/archil/seed.py | 83 | rm -rf $1 && mkdir -p $1 && unzip -q /tmp/q.zip -d $1 && rm /tmp/q.zip | CODE |
| HIGH | managed-agents/self-hosted-sandboxes/archil/seed.py | 84 | find $1 -mindepth 2 -type f -exec mv -t $1 {{}} + 2>/dev/null; find $1 -mindepth 1 -type d -delete | CODE |
| HIGH | managed-agents/self-hosted-sandboxes/archil/seed.py | 95 | curl -fsS -A "$SEC_USER_AGENT" -o $name.zip https://www.sec.gov/Archives/edgar/daily-index/$( [ $name = companyfacts ] | CODE |
| HIGH | managed-agents/self-hosted-sandboxes/archil/seed.py | 96 | mkdir -p $name && unzip -q $name.zip -d $name && rm $name.zip | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | autonomous-coding/autonomous_agent_demo.py | 81 | print("Error: ANTHROPIC_API_KEY environment variable not set") | CODE |
| LOW | autonomous-coding/autonomous_agent_demo.py | 110 | except Exception as e: | CODE |
| LOW | autonomous-coding/agent.py | 92 | except Exception as e: | CODE |
| MEDIUM | autonomous-coding/agent.py | 93 | print(f"Error during agent session: {e}") | CODE |
| LOW | browser-toolset/python/cdp_browser.py | 137 | except Exception: | CODE |
| LOW | browser-toolset/python/cdp_browser.py | 258 | except Exception: | CODE |
| LOW | agents/test_message_params.py | 50 | except Exception as e: | CODE |
| LOW | agents/test_message_params.py | 191 | except Exception as e: | CODE |
| MEDIUM | agents/test_message_params.py | 253 | print("Error: Please set ANTHROPIC_API_KEY environment variable") | CODE |
| LOW | agents/tools/calculator_mcp.py | 50 | except Exception as e: | CODE |
| LOW | agents/tools/file_tools.py | 101 | except Exception as e: | STRING |
| LOW | agents/tools/file_tools.py | 134 | except Exception as e: | CODE |
| LOW | agents/tools/file_tools.py | 229 | except Exception as e: | CODE |
| LOW | agents/tools/file_tools.py | 276 | except Exception as e: | CODE |
| LOW | agents/tools/mcp_tool.py | 38 | except Exception as e: | CODE |
| LOW | agents/utils/history_util.py | 39 | except Exception: | CODE |
| LOW | agents/utils/tool_util.py | 20 | except Exception as e: | CODE |
| LOW | agents/utils/connections.py | 43 | except Exception as e: | CODE |
| MEDIUM | agents/utils/connections.py | 44 | print(f"Error during cleanup: {e}") | CODE |
| LOW | agents/utils/connections.py | 144 | except Exception as e: | CODE |
| MEDIUM | agents/utils/connections.py | 145 | print(f"Error setting up MCP server {config}: {e}") | CODE |
| LOW | computer-use-demo/computer_use_demo/streamlit.py | 534 | except Exception as e: | CODE |
| LOW | computer-use-demo/computer_use_demo/streamlit.py | 547 | except Exception as e: | CODE |
| LOW | computer-use-demo/computer_use_demo/tools/edit.py | 251 | except Exception as e: | CODE |
| LOW | computer-use-demo/computer_use_demo/tools/edit.py | 258 | except Exception as e: | CODE |
| LOW | …gents/self-hosted-sandboxes/daytona/daytona_webhook.py | 246 | except Exception as e: # noqa: BLE001 - one bad item must not stop the drain | CODE |
| LOW | …s/self-hosted-sandboxes/modal/modal_sandbox_webhook.py | 312 | except Exception as e: # noqa: BLE001 - one bad item must not stop the drain | CODE |
| LOW | managed-agents/knowledge-wiki/utilities.py | 103 | except Exception as e: # transient network/API blip: retry | CODE |
| LOW | computer-use-best-practices/computer_use/loop.py | 109 | except Exception as e: | CODE |
| LOW | computer-use-best-practices/computer_use/preflight.py | 57 | except Exception: | CODE |
| LOW | computer-use-best-practices/computer_use/preflight.py | 101 | except Exception: | CODE |
| LOW | computer-use-best-practices/computer_use/tools/batch.py | 75 | except Exception as e: | CODE |
| LOW | …puter-use-best-practices/computer_use/tools/browser.py | 154 | except Exception as e: | CODE |
| LOW | computer-use-best-practices/computer_use/tools/base.py | 126 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/message_handler.py | 119 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/streamlit.py | 137 | except Exception as e: | CODE |
| MEDIUM | browser-use-demo/browser_use_demo/streamlit.py | 138 | print(f"Error adding image to ZIP: {e}") | CODE |
| LOW | browser-use-demo/browser_use_demo/streamlit.py | 520 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/loop.py | 141 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 394 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 413 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 555 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 566 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 613 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 663 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 690 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 715 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 731 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 747 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 811 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 854 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 900 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 1024 | except Exception: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 1043 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 1064 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 1075 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 1101 | except Exception as e: | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 371 | except Exception as e: | STRING |
| MEDIUM | browser-use-demo/tests/test_streamlit_helpers.py | 279 | def run_setup(): | CODE |
| LOW⚡ | browser-use-demo/tests/test_streamlit_helpers.py | 283 | except Exception as e: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | computer-use-demo/computer_use_demo/loop.py | 41 | # The tool_result content a toolset member call receives when an earlier | COMMENT |
| LOW | managed-agents/assistant-ui/app/assistant.tsx | 1 | "use client"; | COMMENT |
| LOW | …nts/assistant-ui/app/api/sessions/[id]/stream/route.ts | 1 | import { client } from "@/lib/anthropic"; | COMMENT |
| LOW | …ts/assistant-ui/app/api/sessions/[id]/confirm/route.ts | 1 | import type { BetaManagedAgentsUserToolConfirmationEventParams } from "@anthropic-ai/sdk/resources/beta/sessions/events" | COMMENT |
| LOW | …aged-agents/assistant-ui/agents/spreadsheet-analyst.md | 1 | --- | COMMENT |
| LOW | …/assistant-ui/lib/managed-agents/session-controller.ts | 1 | "use client"; | COMMENT |
| LOW | …/assistant-ui/lib/managed-agents/session-controller.ts | 41 | private listeners = new Set<Listener>(); | COMMENT |
| LOW | …aged-agents/assistant-ui/lib/managed-agents/reducer.ts | 1 | // The one place that turns a Managed Agents event log into an assistant-ui | COMMENT |
| LOW | …aged-agents/assistant-ui/lib/managed-agents/reducer.ts | 361 | }; | COMMENT |
| LOW | …ssistant-ui/lib/managed-agents/session-list-adapter.ts | 1 | "use client"; | COMMENT |
| LOW | …s/assistant-ui/lib/managed-agents/runtime-provider.tsx | 1 | "use client"; | COMMENT |
| LOW | …s/assistant-ui/lib/managed-agents/runtime-provider.tsx | 61 | // ------------------------------------------------------- per-thread runtime | COMMENT |
| LOW | managed-agents/self-hosted-sandboxes/archil/start.sh | 1 | #!/usr/bin/env bash | COMMENT |
| LOW | …-hosted-sandboxes/archil/environments/self-hosted.yaml | 1 | # The environment, sent by `ant apply` as the Environments API request body. | COMMENT |
| LOW | managed-agents/self-hosted-sandboxes/docker/on-work.sh | 1 | #!/usr/bin/env bash | COMMENT |
| LOW | managed-agents/self-hosted-sandboxes/docker/start.sh | 1 | #!/usr/bin/env bash | COMMENT |
| LOW | …/self-hosted-sandboxes/cloudflare-worker/wrangler.toml | 21 | # sessions until this is a real id. | COMMENT |
| LOW | …s/self-hosted-sandboxes/cloudflare-worker/src/index.ts | 21 | COMMENT | |
| LOW | …-agents/self-hosted-sandboxes/docker-memory/on-work.sh | 1 | #!/usr/bin/env bash | COMMENT |
| LOW | …ed-agents/self-hosted-sandboxes/docker-memory/start.sh | 1 | #!/usr/bin/env bash | COMMENT |
| LOW | …oxes/docker-memory/memory_stores/user-preferences.yaml | 1 | # The memory store, sent by `ant apply` as the Memory Stores API request body. | COMMENT |
| LOW | …f-hosted-sandboxes/cloudflare-containers/wrangler.toml | 21 | tag = "v1" | COMMENT |
| LOW | …ged-agents/self-hosted-sandboxes/openshell/policy.yaml | 41 | port: 443 | COMMENT |
| LOW | …aged-agents/self-hosted-sandboxes/openshell/on-work.sh | 1 | #!/usr/bin/env bash | COMMENT |
| LOW | …aged-agents/self-hosted-sandboxes/openshell/on-work.sh | 161 | # startup. So the token is never in a file, on a command line, in the | COMMENT |
| LOW | managed-agents/self-hosted-sandboxes/openshell/start.sh | 1 | #!/usr/bin/env bash | COMMENT |
| LOW | …lf-hosted-sandboxes/openshell/agents/openshell-demo.md | 1 | --- | COMMENT |
| LOW | …-sandboxes/webhook-demo/environments/webhook-demo.yaml | 1 | # The environment, sent by `ant apply` as the Environments API request body. | COMMENT |
| LOW | …f-hosted-sandboxes/webhook-demo/agents/webhook-demo.md | 1 | --- | COMMENT |
| LOW | managed-agents/linear/src/route-signature.ts | 1 | import { createHmac, timingSafeEqual } from "crypto"; | COMMENT |
| LOW | …naged-agents/daily-brief/agents/daily-brief/vault.yaml | 1 | # The vault: a named container for credentials that Anthropic holds for you and | COMMENT |
| LOW | managed-agents/roadtrip-planner/agents/setup.sh | 1 | #!/usr/bin/env bash | COMMENT |
| LOW | …ged-agents/roadtrip-planner/agents/roadtrip-planner.md | 1 | --- | COMMENT |
| LOW | …d-agents/roadtrip-planner/vaults/roadtrip-planner.yaml | 1 | # The vault. Credentials live here, not in the environment and not in the | COMMENT |
| LOW | managed-agents/mcp-server-typescript/environment.yaml | 1 | # The one Managed Agents resource this quickstart needs: the sandbox template | COMMENT |
| LOW | managed-agents/slack/src/route-signature.ts | 1 | import { createHmac, timingSafeEqual } from "crypto"; | COMMENT |
| LOW | …agents/copilot-kit-ag-ui/agents/financial-assistant.md | 1 | --- | COMMENT |
| LOW | managed-agents/sentry/agents/sentry-triage.md | 1 | --- | COMMENT |
| LOW | managed-agents/chat-sdk/web/app.tsx | 1 | // Browser chat client. The sidebar lists Managed Agents sessions -- the only | COMMENT |
| LOW | managed-agents/chat-sdk/src/app.ts | 1 | // The platform-neutral core: the four /api routes as one fetch-native Hono | COMMENT |
| LOW | managed-agents/chat-sdk/src/bot.ts | 1 | // Chat SDK wiring: the web adapter turns each browser POST into a DM on a | COMMENT |
| LOW | managed-agents/chat-sdk/src/bot.ts | 61 | // Don't use the SDK's per-thread lock for serialization: its TTL (30s) is | COMMENT |
| LOW | managed-agents/chat-sdk/src/managed-agents.ts | 261 | text: string, | COMMENT |
| LOW | computer-use-best-practices/config.example.toml | 1 | # Override any constants.Config field. Point CU_CONFIG at this file (in your | COMMENT |
| LOW | computer-use-best-practices/config.example.toml | 21 | # api_retry_max_attempts = 5 | COMMENT |
| LOW | computer-use-best-practices/requirements.txt | 1 | # This file was autogenerated by uv via the following command: | COMMENT |
| LOW | computer-use-best-practices/requirements.txt | 21 | # via streamlit | COMMENT |
| LOW | computer-use-best-practices/requirements.txt | 41 | gitdb==4.0.12 ; sys_platform == 'darwin' | COMMENT |
| LOW | computer-use-best-practices/requirements.txt | 61 | # via | COMMENT |
| LOW | computer-use-best-practices/requirements.txt | 81 | packaging==26.0 ; sys_platform == 'darwin' | COMMENT |
| LOW | computer-use-best-practices/requirements.txt | 101 | # via | COMMENT |
| LOW | computer-use-best-practices/requirements.txt | 141 | # jsonschema | COMMENT |
| LOW | computer-use-best-practices/requirements.txt | 161 | tenacity==9.1.4 ; sys_platform == 'darwin' | COMMENT |
| LOW | computer-use-best-practices/requirements.txt | 181 | # via | COMMENT |
| LOW | computer-use-best-practices/constants.py | 61 | # Hosted (Anthropic-defined) computer-use tool, used when | COMMENT |
| LOW | computer-use-best-practices/constants.py | 101 | # (including prompt-injection detection on screenshots); the explicit-schema | COMMENT |
| LOW | computer-use-best-practices/constants.py | 121 | # Vision-encoder tiling parameters. The API resizes any image whose long | COMMENT |
| LOW | computer-use-best-practices/constants.py | 161 | # Include the browser / browser_batch tools. | COMMENT |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 221 | # The browser should persist across conversation turns | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | autonomous-coding/security.py | 297 | CODE | |
| LOW | autonomous-coding/agent.py | 23 | CODE | |
| LOW | agents/agent.py | 92 | CODE | |
| LOW | agents/tools/calculator_mcp.py | 13 | CODE | |
| LOW | agents/tools/file_tools.py | 74 | CODE | |
| LOW | agents/tools/file_tools.py | 232 | CODE | |
| LOW | agents/tools/file_tools.py | 89 | CODE | |
| LOW | agents/tools/mcp_tool.py | 24 | CODE | |
| LOW | computer-use-demo/computer_use_demo/streamlit.py | 244 | CODE | |
| LOW | computer-use-demo/computer_use_demo/streamlit.py | 615 | CODE | |
| LOW | computer-use-demo/computer_use_demo/loop.py | 88 | CODE | |
| LOW | computer-use-demo/computer_use_demo/loop.py | 244 | CODE | |
| LOW | computer-use-demo/computer_use_demo/loop.py | 293 | CODE | |
| LOW | computer-use-demo/computer_use_demo/loop.py | 316 | CODE | |
| LOW | computer-use-demo/computer_use_demo/tools/edit.py | 44 | CODE | |
| LOW | computer-use-demo/computer_use_demo/tools/computer.py | 128 | CODE | |
| LOW | managed-agents/knowledge-wiki/build_manifest.py | 52 | CODE | |
| LOW | managed-agents/knowledge-wiki/utilities.py | 67 | CODE | |
| LOW | managed-agents/sentry/managed_agents.py | 84 | CODE | |
| LOW | computer-use-best-practices/tests/test_formatters.py | 26 | CODE | |
| LOW | computer-use-best-practices/computer_use/formatters.py | 23 | CODE | |
| LOW | computer-use-best-practices/computer_use/loop.py | 243 | CODE | |
| LOW | computer-use-best-practices/computer_use/loop.py | 380 | CODE | |
| LOW | browser-use-demo/browser_use_demo/message_renderer.py | 134 | CODE | |
| LOW | browser-use-demo/browser_use_demo/streamlit.py | 113 | CODE | |
| LOW | browser-use-demo/browser_use_demo/streamlit.py | 238 | CODE | |
| LOW | browser-use-demo/browser_use_demo/streamlit.py | 336 | CODE | |
| LOW | browser-use-demo/browser_use_demo/streamlit.py | 531 | CODE | |
| LOW | browser-use-demo/browser_use_demo/streamlit.py | 213 | CODE | |
| LOW | browser-use-demo/browser_use_demo/streamlit.py | 254 | CODE | |
| LOW | browser-use-demo/browser_use_demo/loop.py | 66 | CODE | |
| LOW | browser-use-demo/browser_use_demo/loop.py | 176 | CODE | |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 457 | CODE | |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 616 | CODE | |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 903 | CODE | |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 1104 | CODE | |
| LOW | browser-use-demo/tests/conftest.py | 17 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | autonomous-coding/agent.py | 78 | # Check if command was blocked by security hook | COMMENT |
| LOW | autonomous-coding/agent.py | 124 | # Check if this is a fresh start or continuation | COMMENT |
| LOW⚡ | computer-use-demo/computer_use_demo/tools/edit.py | 91 | # Check if its an absolute path | COMMENT |
| LOW⚡ | computer-use-demo/computer_use_demo/tools/edit.py | 97 | # Check if path exists | COMMENT |
| LOW⚡ | computer-use-demo/computer_use_demo/tools/edit.py | 106 | # Check if the path points to a directory | COMMENT |
| LOW | computer-use-demo/computer_use_demo/tools/edit.py | 162 | # Read the file content | COMMENT |
| LOW | computer-use-demo/computer_use_demo/tools/edit.py | 167 | # Check if old_str is unique in the file | COMMENT |
| LOW | computer-use-demo/image/xvfb_startup.sh | 30 | # Check if Xvfb is already running | COMMENT |
| LOW | browser-use-demo/browser_use_demo/message_renderer.py | 141 | # Check if this is a text extraction result with special markers | COMMENT |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 389 | # Read the file and encode to base64 | COMMENT |
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 366 | # Read the file and encode to base64 | STRING |
| LOW | …-use-demo/browser_use_demo/tools/coordinate_scaling.py | 135 | # Check if coordinates appear to be in Claude's resolution | COMMENT |
| LOW⚡ | browser-use-demo/tests/test_streamlit_helpers.py | 64 | # Set provider to valid enum value so lambda can access it | COMMENT |
| LOW⚡ | browser-use-demo/tests/test_streamlit_helpers.py | 275 | # Set provider to valid enum value so lambda can access it | COMMENT |
| LOW | browser-use-demo/tests/test_streamlit_helpers.py | 23 | # Set provider to valid enum value so lambda can access it | COMMENT |
| LOW | browser-use-demo/tests/test_streamlit_helpers.py | 48 | # Set provider to valid enum value so lambda can access it | COMMENT |
| LOW | browser-use-demo/tests/test_streamlit_helpers.py | 95 | # Set provider to valid enum value so lambda can access it | COMMENT |
| LOW | browser-use-demo/tests/test_integration.py | 240 | # Set provider to valid enum value so lambda can access it | COMMENT |
| LOW | browser-use-demo/tests/test_integration.py | 279 | # Set provider to valid enum value so lambda can access it | COMMENT |
| LOW⚡ | browser-use-demo/tests/test_message_renderer.py | 297 | # Set markdown to raise an exception | COMMENT |
| LOW | browser-use-demo/image/xvfb_startup.sh | 30 | # Check if Xvfb is already running | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | computer-toolset/python/vnc_computer.py | 17 | CODE | |
| LOW | computer-toolset/python/run.py | 20 | CODE | |
| LOW | computer-toolset/python/exercise.py | 19 | CODE | |
| LOW | browser-toolset/python/run.py | 21 | CODE | |
| LOW | browser-toolset/python/exercise.py | 20 | CODE | |
| LOW | browser-toolset/python/cdp_browser.py | 17 | CODE | |
| LOW | agents/__init__.py | 3 | CODE | |
| LOW | agents/__init__.py | 3 | CODE | |
| LOW | agents/__init__.py | 4 | CODE | |
| LOW | agents/tools/__init__.py | 3 | CODE | |
| LOW | agents/tools/__init__.py | 4 | CODE | |
| LOW | agents/tools/__init__.py | 5 | CODE | |
| LOW | agents/tools/__init__.py | 5 | CODE | |
| LOW | agents/tools/__init__.py | 6 | CODE | |
| LOW | agents/tools/__init__.py | 7 | CODE | |
| LOW | agents/tools/mcp_tool.py | 8 | CODE | |
| LOW | agents/utils/__init__.py | 3 | CODE | |
| LOW | agents/utils/__init__.py | 4 | CODE | |
| LOW | …gents/self-hosted-sandboxes/daytona/daytona_webhook.py | 21 | CODE | |
| LOW | …s/self-hosted-sandboxes/modal/modal_sandbox_webhook.py | 36 | CODE | |
| LOW | managed-agents/sentry/oauth_setup.py | 12 | CODE | |
| LOW | …uter-use-best-practices/computer_use/tools/__init__.py | 1 | CODE | |
| LOW | …uter-use-best-practices/computer_use/tools/__init__.py | 1 | CODE | |
| LOW | …uter-use-best-practices/computer_use/tools/__init__.py | 2 | CODE | |
| LOW | browser-use-demo/validate_env.py | 6 | CODE | |
| LOW | browser-use-demo/browser_use_demo/streamlit.py | 10 | CODE | |
| LOW | browser-use-demo/browser_use_demo/loop.py | 5 | CODE | |
| LOW | browser-use-demo/browser_use_demo/tools/__init__.py | 1 | CODE | |
| LOW | browser-use-demo/browser_use_demo/tools/__init__.py | 1 | CODE | |
| LOW | browser-use-demo/browser_use_demo/tools/__init__.py | 1 | CODE | |
| LOW | browser-use-demo/browser_use_demo/tools/__init__.py | 2 | CODE | |
| LOW | browser-use-demo/browser_use_demo/tools/__init__.py | 3 | CODE | |
| LOW | browser-use-demo/browser_use_demo/tools/collection.py | 1 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | browser-toolset/python/cdp_browser.py | 137 | except Exception: | CODE |
| HIGH | computer-use-demo/computer_use_demo/tools/run.py | 38 | except ProcessLookupError: | CODE |
| HIGH | computer-use-best-practices/computer_use/preflight.py | 101 | except Exception: | CODE |
| HIGH | browser-use-demo/browser_use_demo/tools/browser.py | 1024 | except Exception: | CODE |
| HIGH | browser-use-demo/tests/test_message_renderer.py | 182 | except KeyError: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | autonomous-coding/autonomous_agent_demo.py | 84 | print(" export ANTHROPIC_API_KEY='your-api-key-here'") | CODE |
| HIGH | autonomous-coding/README.md | 25 | export ANTHROPIC_API_KEY='your-api-key-here' | CODE |
| HIGH | computer-use-demo/README.md | 50 | export ANTHROPIC_API_KEY=%your_api_key% | CODE |
| HIGH | computer-use-demo/README.md | 180 | export ANTHROPIC_API_KEY=%your_api_key% | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | computer-use-demo/computer_use_demo/tools/edit.py | 193 | # Create a snippet of the edited section | COMMENT |
| MEDIUM | browser-use-demo/browser_use_demo/streamlit.py | 123 | # Create an in-memory ZIP file | COMMENT |
| MEDIUM | browser-use-demo/browser_use_demo/tools/browser.py | 845 | # Create a summary for UI display | COMMENT |
| MEDIUM | browser-use-demo/browser_use_demo/tools/browser.py | 889 | # Create a summary for UI display | COMMENT |
| MEDIUM⚡ | browser-use-demo/tests/test_message_renderer.py | 282 | # Create a mock that doesn't have expected attributes | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | …d-agents/self-hosted-sandboxes/docker-memory/worker.py | 0 | extract the sessions token from a work item's secret payload, or none. | STRING |
| HIGH | …agents/self-hosted-sandboxes/daytona/sandbox_runner.py | 0 | extract the sessions token from a work item's secret payload, or none. | STRING |
| HIGH | …d-agents/self-hosted-sandboxes/modal/sandbox_runner.py | 0 | extract the sessions token from a work item's secret payload, or none. | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | …-use-demo/browser_use_demo/tools/coordinate_scaling.py | 37 | Get the documented size for the given viewport's aspect ratio. Args: viewport_width: Actua | STRING |
| HIGH | …-use-demo/browser_use_demo/tools/coordinate_scaling.py | 77 | Calculate scale factors for converting Claude coordinates to viewport coordinates. Args: v | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | customer-support-agent/README.md | 69 | ## Amazon Bedrock RAG Integration | COMMENT |
| MEDIUM | managed-agents/knowledge-wiki/README.md | 1 | # A knowledge wiki for cheap, correct agentic retrieval | COMMENT |
| MEDIUM | managed-agents/roadtrip-planner/skill.md | 48 | Open <http://localhost:3000>. The page creates one session per browser on load (cookie `roadtrip_planner_session_id`), s | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | autonomous-coding/client.py | 64 | # Create comprehensive security settings | COMMENT |
| MEDIUM | managed-agents/copilot-kit-ag-ui/package-lock.json | 17005 | "resolved": "https://registry.npmjs.org/robust-predicates/-/robust-predicates-3.0.3.tgz", | CODE |
| MEDIUM | browser-use-demo/tests/test_message_renderer.py | 1 | """Tests for MessageRenderer class with comprehensive edge case coverage.""" | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | agents/__init__.py | 6 | __all__ = ["Agent", "ModelConfig", "Tool"] | CODE |
| LOW | agents/tools/__init__.py | 9 | __all__ = [ | CODE |
| LOW | agents/utils/__init__.py | 6 | __all__ = ["MessageHistory", "execute_tools"] | CODE |
| LOW | computer-use-best-practices/computer_use/loop.py | 68 | def _set_trailing_cache_control(messages: list[MessageParam]) -> None: | CODE |
| LOW | …uter-use-best-practices/computer_use/tools/__init__.py | 4 | __all__ = ["Tool", "ToolCollection", "ToolResult"] | CODE |
| LOW | browser-use-demo/browser_use_demo/tools/__init__.py | 5 | __all__ = [ | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …wser_use_demo/browser_tool_utils/browser_dom_script.js | 89 | var placeholder = element.getAttribute("placeholder"); | CODE |
| LOW | …wser_use_demo/browser_tool_utils/browser_dom_script.js | 392 | if (element.getAttribute("placeholder")) | CODE |
| LOW | …wser_use_demo/browser_tool_utils/browser_dom_script.js | 394 | ' placeholder="' + element.getAttribute("placeholder") + '"'; | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | browser-use-demo/browser_use_demo/tools/browser.py | 1104 | CODE |