cro-optimization
Warn
Audited by Snyk on Feb 15, 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). The skill's "Fetch and Extract Landing Page" step explicitly instructs the agent to use WebFetch to retrieve user-provided landing page URLs (arbitrary public websites) and then read and analyze that content, which exposes the agent to untrusted third‑party web content that could carry indirect prompt injections.
Audit Metadata