affinity

Warn

Audited by Snyk on Mar 4, 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 invoking Membrane actions and proxy requests to Affinity (e.g., "Get Notes", "get-list-entries", "membrane request CONNECTION_ID /path/to/endpoint"), which ingest user-generated Affinity data (notes/list entries) that the agent is expected to read and that could contain instructions influencing subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 08:55 AM