outbound-sequences
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's SKILL.md and accompanying resources explicitly require researching and using public, user-generated sources (e.g., "Research Sources" in SKILL.md and resources/response-playbook.yaml listing LinkedIn posts, Twitter/X, company news, job postings, podcasts) as inputs for personalization and message decisions, meaning untrusted third‑party content is expected to be read and can materially influence outreach behavior.
Audit Metadata