automation-workflows
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The playbook explicitly instructs ingesting external user-generated/public content—e.g., "New blog post published on website (via RSS or webhook)", form submissions, and social media posts (LinkedIn/Twitter)—which the agent would read/interpret to generate captions, map fields, or trigger actions, exposing it to untrusted third‑party input.
Audit Metadata