mcp-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 guide explicitly describes Resources and Resource URI patterns that include HTTP endpoints (see "Resource URI Patterns" with http://example.com/api/docs), shows resource handling and examples like "REST API Wrapper
- GitHub API integration" and lists "Integrating external APIs with Claude", which indicates the agent can be made to fetch and ingest arbitrary public HTTP/third-party content that could carry indirect prompt injections.
Audit Metadata