outbound

Warn

Audited by Snyk on Mar 7, 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 autonomously fetches and reads incoming, user-generated emails (see classify-replies SKILL.md step "Read the reply content..." and the list_received_emails / find_reply_threads tools in references/tools-reference.md) and uses their contents to decide tags and follow-up/send/remove actions, so untrusted third-party content can materially change agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 10:52 AM