video-downloader
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or dangerous commands were found. The skill consists entirely of markdown documentation describing functionality without accompanying scripts or executables.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from video platforms, which could contain malicious instructions in metadata. 1. Ingestion points: External URLs provided to the agent as described in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Network access for downloading and file system writes to the user's Downloads folder. 4. Sanitization: Absent.
Audit Metadata