remote-oauth-mcp-pentest

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). Phase 2/3/4/6/7/8/9 require runtime fetching of remote MCP/OAuth/OIDC metadata and endpoints (e.g., .well-known/*, PRM/ASM JSON, and possibly dynamic client registration responses), which are outsider-authored free-form text/JSON that the agent will ingest into its LLM context as evidence.