alphaear-deepear-lite

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow fetches financial signal reports from a third-party hosted JSON endpoint (DeepEar Lite), which can contain outsider-authored text and reasoning ingested directly by the agent.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches financial signal JSON data from an arbitrary Vercel domain with unknown publisher provenance, constituting a weak runtime dependency.