landing-copy
Warn
Audited by Snyk on Mar 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). SKILL.md explicitly states "If the user sends a URL, fetch it and read the copy," which means the agent will retrieve and interpret arbitrary public landing pages (untrusted third‑party web content) as part of its workflow, exposing it to indirect prompt injection risk.
Audit Metadata