video-downloading
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for ingesting untrusted data from x.com status pages, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Twitter/X status URLs (x.com/user/status/ID).
- Boundary markers: None specified in the documentation to distinguish between content and instructions.
- Capability inventory: JavaScript console execution, batch file downloading, and network API requests.
- Sanitization: Implementation details are not provided in the documentation and reside within referenced script files.
Audit Metadata