web-search

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

• Third-party content exposure detected (high risk: 0.90). The skill issues web searches to the public Jina Search endpoint (see search.py URL https://s.jina.ai/?q=... and the SKILL.md description) and prints raw results from third‑party web pages, so the agent will read untrusted public content that could contain instructions affecting its actions.