agent-platforms
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The instructions direct the agent to retrieve a README.md file from an external URL, creating a data ingestion surface where external content could potentially influence agent behavior.
- Ingestion points: Remote README.md file at https://raw.githubusercontent.com/gmh5225/awesome-skills/refs/heads/main/README.md.
- Boundary markers: None provided.
- Capability inventory: General agent capabilities for file retrieval and text processing.
- Sanitization: None.
- [EXTERNAL_DOWNLOADS]: The skill references a documentation resource hosted on GitHub, which is recognized as a well-known hosting service.
Audit Metadata