bubble
Warn
Audited by Snyk on Apr 22, 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). The skill's SKILL.md shows the agent uses Membrane to call Bubble APIs (e.g., "list-records", "get-record", and "membrane request ...") which fetch and interpret data from users' Bubble apps (third-party, user-generated content) and can drive actions/workflows, so external content could influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata