web-test
Warn
Audited by Snyk on May 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: 0.80). The skill explicitly navigates to and automates arbitrary web URLs supplied to the runner (e.g., "node $RUN run script.js" and connect/createContext in SKILL.md and browser.mjs), reads and interprets page DOM (getFormState/readTable/readSpreadsheet/clickElement) and then makes action decisions, so untrusted or user-provided web content can directly influence automated actions and thus enable indirect prompt-injection-like influence.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata