mcp-builder
Warn
Audited by Snyk on Sep 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow uses an evaluation harness (
scripts/evaluation.py) that processes evaluation tasks from XML files containing arbitrary user-authored questions, exposing the evaluating agent to untrusted text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata