youtube-deepdive
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The tool usage is consistent with the skill's stated purpose.
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill extracts untrusted data from external YouTube video pages (descriptions and comments), creating a surface for potential instruction injection. 1. Ingestion points: YouTube video pages via browser snapshots (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Browser navigation and interaction tools, and local file writing (SKILL.md). 4. Sanitization: Absent.
Audit Metadata