write-a-skill
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an external GitHub repository for attribution in reference.md.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined descriptions to generate new skills, creating a potential ingestion point for untrusted instructions.
- Ingestion points: User requests to create or improve skills in SKILL.md.
- Boundary markers: Not explicitly defined for generated output.
- Capability inventory: File modification and creation within the repository.
- Sanitization: No specific filtering for input instructions.
Audit Metadata