boost
Warn
Audited by Snyk on Apr 21, 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 "Proxy requests" workflow (membrane request CONNECTION_ID /path/to/endpoint) instructs the agent to fetch data from Boost's APIs via Membrane, which can return untrusted, user-generated social media content that the agent is expected to read and that could materially influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata