i-critique
Warn
Audited by Snyk on Apr 10, 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's Step 2 (Assessment A and the "Browser visualization" flow) explicitly instructs the agent to open and visually inspect live pages by navigating to a page via a direct URL, read HTML/CSS/JS, inject scripts, and read console output—which requires fetching and interpreting arbitrary web content that could be untrusted and influence the agent's decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata