headless-web-viewer
Warn
Audited by Snyk on Mar 9, 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 CLI and docs (scripts/render_url_playwright.mjs and SKILL.md/README usage) explicitly load arbitrary URLs via page.goto(args.url) and then extract/print/save the rendered HTML and document.body.innerText (out-html/out-text/--print), so the agent will consume untrusted, public web content as part of its workflow.
Audit Metadata