ptlam-code-style-python-fastapi
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to read and follow instructions from local repository files, such as
AGENTS.mdandpyproject.toml, to determine project-specific requirements and permitted exceptions. This creates an attack surface where malicious instructions embedded in a repository could influence the agent's actions or behavior. - Ingestion points: The
SKILL.mdandskills/ptlam-code-style-python/SKILL.mdfiles (Step 1 under 'Before review or change') explicitly direct the agent to 'read every applicable AGENTS.md'. - Boundary markers: The instructions do not provide explicit boundary markers or warnings to isolate these external instructions from the agent's core safety directives.
- Capability inventory: The agent is instructed to perform tasks using file system access and shell execution for tools like
uv,ruff,pytest, andalembic. - Sanitization: No sanitization or validation mechanism is mentioned for the content read from these repository files.
Audit Metadata