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 live JSON from the public URL https://deepear.vercel.app/latest.json (see SKILL.md and scripts/deepear_lite.py) and directly ingests/display fields such as "reasoning", "summary", and "sources" into its reports, so untrusted third‑party content can influence agent outputs and decisions.