sendblue
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 SKILL.md explicitly instructs the agent to proxy arbitrary requests to the Sendblue API via Membrane (see "Proxy requests" and "Running actions" sections using
membrane request CONNECTION_ID /path/to/endpointand action runs), which fetches and interprets third‑party Sendblue data (contacts/messages) that can be user-generated and can materially influence which actions the agent chooses to run.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata