thumbnail-concepts
Warn
Audited by Snyk on Nov 21, 2026
Risk Level: MEDIUM
Full Analysis
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 outlier searches (SKILL.md line 22) that return outsider-authored YouTube videos, with their titles, channel names, and thumbnail images, which the agent then views and analyses (line 23); the attacker can publish poisoned videos but cannot force them into the agent's search results.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata