botpress
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 shows the agent calling Membrane/Botpress actions like "list-messages" and "get-message" (and using the proxy request command) to retrieve conversation messages and events (user-generated content) from Botpress, which the agent would read and could materially influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata