code-review-recon
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external source code via the
code_pathinput, which constitutes a standard surface for indirect prompt injection where malicious instructions within the code could attempt to influence the agent. - Ingestion points: The skill processes external files located at the directory path provided in the
code_pathparameter. - Boundary markers: The instructions do not mandate the use of specific delimiters or safety warnings for the agent to use when reading the external code content.
- Capability inventory: The skill utilizes the agent's file system access and code interpretation capabilities to perform its reconnaissance tasks.
- Sanitization: Source code is analyzed in its raw form to ensure the completeness and accuracy of the resulting security map.
Audit Metadata