agent-zero

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly allows and uses a "web" tool (see "Allowed tools: web, filesystem, shell, python" in SKILL.md) and provides example research tasks (e.g., "Research the latest trends in AI agent frameworks") that indicate the agent will fetch and interpret public web content, so untrusted third‑party pages could influence its actions.