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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 22, 2026, 02:01 PM
Issues
1