outlook
Warn
Audited by Snyk on Feb 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md shows the agent can list and fetch user email and message bodies via Microsoft Graph through the gateway (e.g., GET /outlook/v1.0/me/messages and GET /outlook/v1.0/me/messages/{messageId}), meaning it ingests untrusted, user-generated email content that the agent may read and then use to drive actions (send mail, create events, move messages), enabling indirect prompt injection.
Audit Metadata