output-customization

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

• Third-party content exposure detected (high risk: 0.80). This skill's mandatory audit workflow (see SKILL.md sections "External Technology Validation" and "MANDATORY: Use docs-management BEFORE Any Finding") requires querying public MCP servers and search/aggregation sites (e.g., microsoft-learn, perplexity, context7) and invoking docs-management to load external documentation, so the agent ingests third‑party web content that can materially influence decisions.