43-drei
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to inspect the existing repository and dependencies, which creates a surface for indirect prompt injection if the project being audited contains malicious instructions in its files.
- Ingestion points: The 'AI implementation contract' in SKILL.md instructs the agent to 'Inspect the existing repository, framework, dependencies, and conventions'.
- Boundary markers: Absent. The instructions do not specify how the agent should distinguish between legitimate code and potentially malicious instructions embedded in the repository.
- Capability inventory: The skill assumes the agent has standard repository management capabilities, including file system access for inspection and code generation.
- Sanitization: Absent. There are no instructions to sanitize or validate content read from the repository files.
Audit Metadata