agent-context-validator

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires checking external references and web resources (e.g., "External references checked (URLs return 200)" in the Validation Checklist and the Imported Agent Spec listing WebSearch / mcp__brave__brave_web_search), so the agent will fetch and interpret public third‑party content that could contain untrusted instructions.