alphaear-deepear-lite

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and parses live JSON from the public URL https://deepear.vercel.app/latest.json (see scripts/deepear_lite.py and SKILL.md), ingesting untrusted "signals" including "reasoning" and "summary" fields that the agent reads and returns and which could materially influence subsequent decisions or actions.