config-validation

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses the docs-research skill to fetch “canonical OpenClaw documentation URL map” and “latest information” from the web at runtime, so the agent ingests public web content (outsider-authored prose) into the LLM context via the docs-research toolchain (e.g., Firecrawl/Exa/WebFetch).