integrating-agent-auth

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow (Step 4 "Call the third-party API" and the "Building agents" examples) explicitly fetches user-generated content from third-party connectors (e.g., Gmail via the Gmail API, and it mentions Slack/Notion/calendar connectors) and has agents read/summarize that content, which could contain untrusted instructions that influence agent decisions.