hotjar
Warn
Audited by Snyk on Apr 4, 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). This skill explicitly reads Hotjar user-generated data (e.g., "Recordings", "Feedback", "Surveys") via Membrane and even allows arbitrary proxied API requests ("membrane request CONNECTION_ID /path/to/endpoint") so the agent would fetch and interpret untrusted third-party content from public websites.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata