A Codex jailbreak prompt and test pack for gpt. 针对 gpt 系列的 Codex 破甲提示词与测试包。
This report summarizes scanner evidence for MDX-Tom/gpt-instruct, a Python project with 9,822 GitHub stars. SynthScan examined 4,528 lines of code across 17 source files, recording 53 pattern matches distributed across 4 syntactic categories. The legacy adjusted pattern signal is 15.9 (Elevated 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? 37 finding(s).
Are imports declared and package/API names verified? 8 finding(s).
Are wrappers, guards, and repeated structures necessary? 42 finding(s).
Which changes need focused human review? 53 finding(s).
Run additional scans to build a history of the legacy pattern signal. Score changes are not a measure of AI adoption or code quality.
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 53 distinct pattern matches across 4 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 | codex-instruct.py | 190 | def is_valid_instruction_line(line: object) -> bool: | STRING |
| LOW | codex-instruct.py | 199 | def top_level_model_instructions_line(text: str) -> str | None: | STRING |
| LOW | codex-instruct.py | 210 | def line_references_managed_prompt(line: str | None, filenames: set[str]) -> bool: | CODE |
| LOW | codex-instruct.py | 224 | def replace_top_level_model_instructions(text: str, replacement: str | None) -> str: | CODE |
| LOW | codex-instruct.py | 340 | def previous_instruction_from_legacy_baseline(config_path: Path) -> str | None: | CODE |
| LOW | codex-instruct.py | 399 | def restore_managed_model_instructions(config_path: Path) -> tuple[bool, str]: | CODE |
| LOW | sync-archives.py | 77 | def write_single_file_archive(source: Path, destination: Path, archive_name: str) -> None: | CODE |
| LOW | unit-tests/test_codex_instruct.py | 146 | def test_interactive_menu_selects_each_packaged_version(self) -> None: | CODE |
| LOW | unit-tests/test_codex_instruct.py | 169 | def test_round_trip_restores_previous_instruction_entry(self) -> None: | CODE |
| LOW | unit-tests/test_codex_instruct.py | 192 | def test_nested_assignment_is_not_rewritten(self) -> None: | CODE |
| LOW | unit-tests/test_codex_instruct.py | 215 | def test_legacy_baseline_migrates_only_previous_instruction(self) -> None: | CODE |
| LOW | unit-tests/test_codex_instruct.py | 240 | def test_full_reset_removes_state_and_prompt_without_reverting_provider(self) -> None: | CODE |
| LOW | unit-tests/test_codex_instruct.py | 275 | def test_crlf_line_endings_are_preserved(self) -> None: | CODE |
| LOW | unit-tests/test_codex_instruct.py | 285 | def test_tampered_state_cannot_nominate_config_for_deletion(self) -> None: | CODE |
| LOW | unit-tests/test_codex_instruct.py | 315 | def test_modified_custom_prompt_is_preserved_on_reset(self) -> None: | CODE |
| LOW | unit-tests/test_codex_instruct.py | 341 | def test_atomic_config_update_preserves_symlink(self) -> None: | CODE |
| LOW | unit-tests/test_codex_instruct.py | 359 | def test_external_path_with_managed_basename_is_not_owned(self) -> None: | CODE |
| LOW | unit-tests/test_codex_instruct.py | 369 | def test_preexisting_unowned_prompt_is_not_overwritten(self) -> None: | CODE |
| LOW | unit-tests/test_codex_instruct.py | 386 | def test_explicit_snapshot_restore_keeps_manual_recovery(self) -> None: | CODE |
| LOW | unit-tests/test_codex_instruct.py | 403 | def test_legacy_preexisting_prompt_is_preserved(self) -> None: | CODE |
| LOW | unit-tests/test_archive_sync.py | 21 | def test_archive_specs_never_target_examples(self) -> None: | CODE |
| LOW | unit-tests/test_archive_sync.py | 26 | def test_matching_archive_is_detected_without_metadata_rewrite(self) -> None: | CODE |
| LOW | unit-tests/test_archive_sync.py | 43 | def test_changed_source_marks_archive_stale(self) -> None: | CODE |
| LOW | unit-tests/test_star_history.py | 112 | def test_renderer_fallback_and_annotation_policy(self) -> None: | CODE |
| LOW | unit-tests/test_star_history.py | 157 | def test_repository_seed_passes_schema_validation(self) -> None: | CODE |
| LOW | unit-tests/test_star_history.py | 169 | def test_metadata_request_does_not_list_stargazers(self) -> None: | CODE |
| LOW | unit-tests/test_star_history.py | 200 | def test_current_record_coalesces_same_day_and_appends_next_day(self) -> None: | CODE |
| LOW | unit-tests/test_star_history.py | 235 | def test_deployed_data_preferred_with_guarded_seed_fallbacks(self) -> None: | CODE |
| LOW | unit-tests/test_star_history.py | 339 | def test_pipeline_contains_no_hosted_service_or_stargazer_listing(self) -> None: | CODE |
| LOW | unit-tests/test_star_history.py | 353 | def test_patch_seeds_local_cache_and_is_idempotent(self) -> None: | CODE |
| LOW | unit-tests/test_star_history.py | 370 | def test_patch_rejects_unexpected_upstream_source(self) -> None: | CODE |
| LOW | .github/scripts/star_history.py | 295 | def fetch_repository_star_count(repository: str, token: str) -> int: | CODE |
| LOW⚡ | .github/scripts/star_history.py | 466 | def validate_local_backend_url(value: str) -> str: | CODE |
| LOW⚡ | .github/scripts/star_history.py | 475 | def validate_fallback_base_url(value: str) -> str: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | .github/scripts/star_history.py | 86 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | .github/scripts/star_history.py | 88 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | .github/scripts/star_history.py | 150 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | .github/scripts/star_history.py | 152 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | .github/scripts/star_history.py | 399 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | .github/scripts/star_history.py | 401 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | .github/scripts/star_history.py | 461 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | .github/scripts/star_history.py | 463 | # --------------------------------------------------------------------------- | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | codex-instruct.py | 11 | CODE | |
| LOW | sync-archives.py | 4 | CODE | |
| LOW | unit-tests/test_codex_instruct.py | 1 | CODE | |
| LOW | unit-tests/test_archive_sync.py | 1 | CODE | |
| LOW | unit-tests/test_star_history.py | 1 | CODE | |
| LOW | .github/scripts/star_history.py | 15 | CODE | |
| LOW | .github/scripts/build_pages_readme.py | 4 | CODE | |
| LOW | .github/scripts/build_pages_readme.py | 10 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | codex-instruct.py | 620 | CODE | |
| LOW | codex-instruct.py | 726 | CODE | |
| LOW | .github/scripts/build_pages_readme.py | 178 | CODE |