elixir-docs-review
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Elixir source code (.ex, .exs) and documentation content. This creates an attack surface where maliciously crafted comments or docstrings within the files being reviewed could attempt to mislead the agent's logic or override its review instructions.
- Ingestion points: Analyzes user-provided Elixir modules, function definitions, and documentation blocks as specified in the 'Review Checklist' and 'Scope lock' gate.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the code being analyzed.
- Capability inventory: Reads file contents, performs qualitative assessment of documentation, and generates a review report; the skill also references using test output (mix test) for verification.
- Sanitization: No sanitization or filtering logic is prescribed for handling external code or documentation data before it is processed by the agent.
Audit Metadata