dev-context-code-graph
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The core functionality of the skill is limited to local static analysis of source code to generate structured relationship maps.
- [DYNAMIC_EXECUTION]: The regression test suite located in scripts/test_code_graph_regressions.py utilizes importlib.util to dynamically load adjacent scripts for validation purposes. This is a controlled use of dynamic loading for development testing and does not ingest untrusted external input.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code as its primary input. While this presents an attack surface, the risk is mitigated as the skill only performs static parsing (AST or regex) and does not execute the code it scans. Furthermore, the report generation script (scripts/export_code_graph_report.py) implements HTML entity escaping to prevent cross-site scripting risks in the generated artifacts.
- [SAFE]: The repository scanner (scripts/scan_code_repo.py) implements a strict blacklist for sensitive and large directories, including .git, node_modules, and .venv, ensuring that only relevant source code is processed and preventing accidental metadata exposure.
Audit Metadata