deep-repo-code-scan
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies and processes data from external sources within the repository, creating a surface for indirect prompt injection.\n
- Ingestion points: Reads repository files,
AGENTS.md, governing documentation, and git status (SKILL.md).\n - Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between its own logic and instructions that might be embedded in the audited code or documentation.\n
- Capability inventory: The skill utilizes
ripgrep,git, and local build/test tools. It is also capable of modifying repository files if requested by the user.\n - Sanitization: There is no evidence of sanitization or filtering of the content ingested from the scanned repository.\n- [COMMAND_EXECUTION]: The skill uses several command-line tools for analysis.\n
- Evidence: Uses
rg(ripgrep),wc,git, and refers to tools likeKnipandReact Doctorfor static analysis and diagnostics. These are standard tools for the skill's documented purpose.
Audit Metadata