unifuncs-deep-search

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

• Third-party content exposure detected (high risk: 0.90). The skill's primary workflow (SKILL.md and deep-search-report.py / deep-search-create-task.py / deep-search-query-task.py) sends queries to UniFuncs' API endpoints (e.g., https://api.unifuncs.com/deepsearch/...), which perform deep web searches and return streamed/aggregated content from public websites and user-generated sources that the agent reads and uses to produce reports, so untrusted third‑party content can materially influence its outputs and actions.