python-code-style
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Python source code and project metadata to contextualize comments and docstrings into problem-specific documentation.
- Ingestion points: Reads user-owned Python files (e.g., in
src/,experiments/,audit/,data/eda.py) and project-level context such as design notes and goals. - Boundary markers: The instructions do not define specific delimiters or boundary markers to isolate ingested content from the agent's internal reasoning.
- Capability inventory: The skill uses file-writing tools to modify source code files after the documentation pass.
- Sanitization: No explicit sanitization or filtering mechanisms are described for the ingested text before it is interpolated into the agent's generation process.
- [COMMAND_EXECUTION]: The skill instructs the agent to run the
ruffutility (e.g.,pixi run ruff format <files>,pixi run ruff check --fix <files>) inside the project's environment. This is a standard operation for a code-style skill and utilizes a well-known, established linting tool.
Audit Metadata