production-code-audit
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing untrusted source code, which creates a surface for indirect prompt injection if the audited files contain malicious instructions. \n
- Ingestion points: The skill instructs the agent to read all files in the target repository completely (specified in references/detailed-guide.md). \n
- Boundary markers: There are no specific technical delimiters or instructions to treat codebase content as non-executable text provided to the agent. \n
- Capability inventory: The skill is authorized to perform file writes ("targeted repairs") and execute validation tests. \n
- Sanitization: While it provides instructions to inspect scripts before execution and use parameterization for repairs, it lacks a mechanism to specifically filter out or ignore instructions embedded within the ingested data.
Audit Metadata