mcp-builder
Warn
Audited by Snyk on Aug 26, 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 runtime evaluation harness in scripts/evaluation.py ingests outsider-authored free text by parsing an XML evaluation file (question/answer strings) and passing the directly as the user message to the LLM via messages=[{"role":"user","content": question}].
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata