discovery-mechanisms
Warn
Audited by Snyk on Jul 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The required workflow involves the MCP client fetching RFC 8414/OIDC “/.well-known” metadata from authorization servers at runtime (public web content), which is outsider-authored JSON that the client parses and then uses in the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata