goap-agent

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly includes a "web-doc-resolver" research skill (see skills.md and its use in examples.md / patterns.md) that resolves web/docs sources into compact markdown and is invoked as a required research step, so the agent ingests public third‑party web content that can influence planning and actions.