prompt-engineer-pro

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

• Third-party content exposure detected (high risk: 0.90). The skill's prompt and patterns explicitly include web-browsing tools and web search in required workflow sections (e.g., the Kimi "Available Tools" list includes mshtools-web_search and mshtools-browser_* and references/03-state-machine-planning.md states "While in 'planning': ... browse web"), meaning the agent is expected to fetch and read public web content that can influence its planning and actions.