typebot
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.md explicitly instructs using Membrane to proxy requests to the Typebot API (see "Proxy requests") and to fetch "Result" objects/submissions (user-generated content), so the agent will ingest and act on untrusted third-party content from Typebot that could contain injected instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata