gatherup
Warn
Audited by Snyk on Apr 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly exposes the agent to user-generated third‑party content via GatherUp actions such as "Get Online Reviews" (which pulls reviews from Google, Yelp, Facebook, etc.) and via Membrane proxy requests to GatherUp APIs, so the agent will fetch and read untrusted public reviews that could materially influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata