youtube-retention
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill instructions are purely informational and guide the AI in providing feedback on video retention data. No malicious patterns or security risks were found. No tools, network access, or file system permissions are requested.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-pasted retention curve data, which is an ingestion surface for untrusted data.
- Ingestion points: User input described in the argument-hint.
- Boundary markers: None present in the instructions.
- Capability inventory: None. The skill does not use tools, perform network requests, write to files, or execute commands.
- Sanitization: None present. Because the skill lacks any dangerous capabilities, this surface presents no actionable risk.
Audit Metadata