relevance-ai

Warn

Audited by Snyk on Apr 2, 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 instructs the agent to fetch and run actions against Relevance AI (third-party) data — e.g., via "membrane action run" and the "membrane request CONNECTION_ID /path/to/endpoint" proxy in SKILL.md — which will ingest and interpret user-generated/untrusted documents/chunks from Relevance AI and could therefore influence subsequent decisions or tool use.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 2, 2026, 07:19 AM
Issues
1