ask-ui
Warn
Audited by Snyk on Aug 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required runtime workflow starts a local HTTP server in
scripts/ask-ui.mjsand serves a browser UI that ingests outsider-authored free text submitted through/api/sessions/:sessionId/rounds/:roundNumber/answers(client-controlledcustomText/answers) and then returns it to the calling workflow.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The skill's served UI page includes and will fetch/execute the remote script https://cdn.bootcdn.net/ajax/libs/tailwindcss-browser/4.1.13/index.global.min.js at runtime (index.html), which loads external code into the agent's runtime UI.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata