supernotes
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 explicitly fetches and operates on Supernotes content via Membrane (e.g., "membrane action run --connectionId=CONNECTION_ID ..." and "membrane request CONNECTION_ID /path/to/endpoint"), which causes the agent to ingest user-generated/third-party notes and attachments that could contain instructions influencing subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata