research

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: 0.80). The skill's required workflow (Step 2: "Research the Target" and Outreach Prep) explicitly instructs enriching people/companies and using LinkedIn URLs, "recent activity/post", and "Recent Signals: news, funding, hiring" — i.e., ingesting public/social/website content to personalize outreach and drive next actions — which clearly exposes the agent to untrusted third‑party user-generated content that can influence behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 03:09 AM