codebase-audit
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external source code and documentation, creating a surface for indirect prompt injection where malicious instructions embedded in the analyzed repository could influence agent behavior.
- Ingestion points: As described in SKILL.md, the agent reads various files including READMEs, configuration manifests (e.g., package.json), and source code files.
- Boundary markers: The instructions do not define clear delimiters or specific guidance to treat content from the audited repository as passive data rather than instructions.
- Capability inventory: The skill utilizes shell tools like git and grep, can spawn subagents, and is instructed to perform web research for dependency verification.
- Sanitization: There are no requirements or methods mentioned for sanitizing or filtering the content ingested from the external repository.
Audit Metadata