cold-outreach-sequence
Warn
Audited by Snyk on Feb 21, 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.md workflow explicitly requires researching and using open/public third‑party sources — e.g., "Where to look: Their LinkedIn activity, Company news (Crunchbase, TechCrunch), Their website, Podcasts" — and instructs the agent to read and incorporate that untrusted/user-generated content into outreach messages, which could materially influence actions.
Audit Metadata