visual-qa

Warn

Audited by Snyk on Mar 1, 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 required workflow explicitly opens and navigates a supplied URL (Setup: "Override | /visual-qa https://staging.example.com" and steps using "agent-browser open {URL}{ROUTE}") and then reads/interprets screenshots of that live app content (Workflow step 3–4), so untrusted third‑party webpages could be ingested and influence fixes/decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 02:02 AM