game-changing-features
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data (the user's codebase) to perform strategic analysis, which creates a surface for indirect prompt injection.
- Ingestion points: The
SKILL.mdfile (Workflow Step 1) instructs the agent to "Research the codebase, look at existing features" to understand the product. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between legitimate code and potentially malicious instructions embedded within the code being analyzed.
- Capability inventory: The skill has read access to the entire codebase and write access to the filesystem (saving session reports to
.claude/docs/ai/<product-or-area>/10x/session-N.md). - Sanitization: There is no mention of sanitizing or escaping the content read from the codebase before it is processed or written to the output documentation.
Audit Metadata