research

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md states it performs "comprehensive research grounded in web data" and the required scripts/research.sh make a POST to the external API at https://api.inspiro.top/research, meaning the agent ingests third‑party web-sourced content returned by that service which can influence its outputs.