ms365

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly retrieves user-generated mailbox content (including full email bodies) from Microsoft Graph — see scripts/src/email.ts and the SKILL.md/README instructions for "Reading Emails" — so the agent will ingest potentially untrusted third-party content that could contain instructions influencing its actions.