jina-s

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 explicitly instructs using s.jina.ai to perform web searches and return SERP results, meaning the agent will fetch and read untrusted public web content (search results) as part of its workflow, which could include user-generated or third-party pages that might inject instructions.