leanmcp-builder

Warn

Audited by Snyk on Feb 16, 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 includes an ApiService example (references/decorators.md) that uses fetch(args.endpoint) and returns response.json(), which would cause the agent to call and ingest arbitrary user-provided/public URLs and their untrusted content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:45 AM