roast-my-plan
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to inspect the user's codebase to answer design questions, which introduces an indirect prompt injection surface.
- Ingestion points: The agent reads local codebase files as specified in SKILL.md.
- Boundary markers: No specific delimiters are defined to separate the data in the codebase from instructions.
- Capability inventory: The skill relies on the agent's file-reading tools to access project contents.
- Sanitization: There are no explicit instructions to sanitize or filter the content of the files being read.
Audit Metadata