authentication

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

• Third-party content exposure detected (high risk: 0.70). The skill directly fetches and consumes public third-party data — for example the OAuth/OIDC flows (server_metadata_url for Google and other providers) and OIDCValidator.get_jwks which does an HTTP GET to {issuer}/.well-known/jwks.json and uses provider token/userinfo in the oauth callbacks — and that external metadata/JWKS/userinfo is parsed and used to validate tokens and drive authentication/authorization decisions, so it can materially influence behavior.