oauth-integrations

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

• Third-party content exposure detected (high risk: 0.80). The skill's runtime examples and guidance explicitly fetch and parse data from public third-party APIs — e.g., https://api.github.com/user and https://graph.microsoft.com/v1.0/me (and /user/emails) — which return user-generated/untrusted profile content that the agent is expected to read and interpret.