respondio
Warn
Audited by Snyk on Apr 30, 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.md instructs using the Membrane CLI to connect to Respond.io and run actions (e.g., "membrane action run" and listing conversation/contact resources) which will fetch user-generated messages from public messaging channels (WhatsApp, Messenger) — untrusted third-party content the agent is expected to read and could materially influence actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata