build

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

• Third-party content exposure detected (high risk: 0.90). This skill's browse-qa gear (see SKILL.md default chain and the --url input) and the Browse QA blueprint (references/02_BROWSE_QA_BLUEPRINT.md) open arbitrary target URLs with the OpenClaw browser, ingest page content, screenshots, and console logs, and use pass/fail results to drive next actions (e.g., ship/commit), so untrusted third-party pages can materially influence the agent's decisions and tool use.