configuring-oauth2-authorization-flow

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

• Third-party content exposure detected (high risk: 0.90). The skill's runtime scripts (scripts/agent.py's discover_oauth_endpoints and scripts/process.py's _audit_discovery_endpoint) fetch and parse public .well-known/openid-configuration from arbitrary issuer URLs provided at runtime, ingesting untrusted, user-supplied web JSON that directly influences audit findings and token-testing actions.