email-composer

Warn

Audited by Snyk on Mar 1, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). SKILL.md (Workflow step 1) explicitly directs the agent to "use search_web to find the recipient's core intellectual thesis, recent publications, or public statements," which requires fetching and interpreting untrusted public web content that will directly influence email drafting.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 01:34 AM