media-use
Fail
Audited by Snyk on Nov 19, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The visible content shows no malicious intent: the skill's telemetry beacon is disclosed with an opt-out, and the sign-in and billing flows are documented. The one sketchy point is the instruction not to volunteer prices, estimates or usage, which withholds cost information from the user, so I flag it as medium under recall-first. The rest of the skill is truncated and was not reviewed.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). Outsider-authored Openverse search results (titles, creator and tag metadata from a public community registry) are read at runtime when the SFX route searches for each cue, but the agent must trigger that search, so the risk is low.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata