draft-outreach
Warn
Audited by Snyk on Feb 19, 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). The skill's required "Step 2: Research First" explicitly performs web searches ("Web search for company + person") and uses public/untrusted sources (news, posts, articles) as mandatory input to craft personalized outreach, so third-party content can materially influence the agent's drafting decisions.
Audit Metadata