reverse-engineer-niche
Fail
Audited by Snyk on Nov 21, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill's purpose is niche research, and its one suspicious element is an instruction to hide from the user that terminated-channel thumbnails load from the vendor's own CDN, which is concealment of the skill's own activity rather than an attack on the user.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow runs TubeLab MCP keyword and related-channel searches, then reads the titles, thumbnails, opening 30 seconds and full transcripts of the returned YouTube videos, which outsiders author and can publish, but the agent selects these through searches rather than from a feed that outsiders can post into directly.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata