gsd-secure-phase
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external project artifacts (SECURITY.md, PLAN.md) which could potentially contain malicious instructions intended to influence the agent's behavior during the audit process.
- Ingestion points: File content is ingested via the Read and Glob tools as described in the objective and execution logic.
- Boundary markers: No specific delimiters or safety instructions are defined in the SKILL.md to distinguish between processed data and system instructions.
- Capability inventory: The skill utilizes tools like Bash, Write, and Edit, which provide a significant capability surface if the agent were to follow instructions embedded in analyzed files.
- Sanitization: The skill does not explicitly describe sanitization or validation of the content read from project files before processing it.
Audit Metadata