repo-style
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No executable code, scripts, or binary files are included in the skill.
- [SAFE]: The skill explicitly advises keeping sensitive material out of public documentation and following project-specific secret-handling conventions.
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to read project-specific instructions (e.g., AGENTS.md), creating a surface for indirect prompt injection. Ingestion points: Project entry points and AGENTS.md (SKILL.md). Boundary markers: Absent. Capability inventory: None (no code provided). Sanitization: Absent. This surface is considered safe given the lack of executable tools.
Audit Metadata