miniproject

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md Research stage explicitly instructs the agent to use external web search/extraction tools ("use_skill(brave_search) with its search and content extraction scripts" and fallback to lynx CLI) to gather information from public websites, meaning the agent will fetch and read untrusted third-party web content as part of its required workflow.