snatchbot
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: 0.70). This skill explicitly lets the agent fetch and interact with SnatchBot data via Membrane (see "Proxy requests" / "membrane request CONNECTION_ID /path/to/endpoint" and the various "Flow/Content" actions), which exposes arbitrary, user-generated third‑party content (bot flows, messages, templates) that the agent is expected to read and could materially influence its subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata