python-coding-standards
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes repository files and metadata for code review and refactoring, creating a vulnerability surface for indirect prompt injection. 1. Ingestion points: Agent reads source code and pyproject.toml from the repository (SKILL.md, references/project-environment.md). 2. Boundary markers: The skill instructions lacks specific delimiters to separate code from instructions or warnings to ignore embedded prompts. 3. Capability inventory: The skill utilizes uv run, uv sync, and uv add to execute shell commands and manage dependencies (references/project-environment.md). 4. Sanitization: No content filtering is described before the agent processes the repository files.
- [EXTERNAL_DOWNLOADS]: The skill references an external Pydantic skill hosted on GitHub (https://github.com/pydantic/skills) and uses the uv package manager to install dependencies from PyPI.
- [COMMAND_EXECUTION]: The skill guides the agent to execute shell commands such as uv run pytest and uv run ruff check for code validation.
Audit Metadata