goap-agent

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly invokes a "web-search-researcher" skill in examples and patterns (see examples.md Phase 1 and patterns.md Phase 2 / skills.md "web-search-researcher") to perform web research from the open web, which means the agent will fetch and act on untrusted public third‑party content that can influence planning and tool use.