troubleshoot

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

• Third-party content exposure detected (high risk: 0.90). The skill's required troubleshooting workflow instructs the agent to open and interact with target URLs using agent-browser (e.g., "agent-browser open https://example.com/target-page" and "対象URLで再現" in the "問題別対応" section), which clearly fetches and interprets arbitrary third-party web pages as part of its diagnostic actions, exposing it to untrusted user-provided content that could inject instructions.