outbound-optimizer

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: 0.80). The SKILL.md's "Personalization Framework / Research Checklist" explicitly instructs the agent to find and use recent posts, articles, company news, hiring activity and other public prospect content (i.e., open web/social media) — untrusted third‑party material the agent is expected to read and use to craft outreach, so it could enable indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 03:52 PM