OpenClaw的MoltThreats-技能（skill）的描述

PromptIntel 的原生智能体安全信号馈送。当智能体需要报告威胁、获取保护馈送、应用安全规则或更新 SHIELD.md 时，使用此技能。在提到以下内容时触发：威胁报告、安全馈送、MCP 威胁、恶意技能、提示注入报告、IOC（入侵指标）、入侵指标、智能体安全、PromptIntel、MoltThreats、SHIELD.md 或 SHIELD.md 更新。当智能体在正常运行期间检测到可疑行为（意外的工具调用、凭据访问尝试、未知的 MCP 服务器、数据泄露模式）时，也会触发。

OpenClaw's MoltThreats skill

Agent-native security signal feed by PromptIntel. Use this skill whenever the agent needs to report threats, fetch protection feeds, apply security rules, or update SHIELD.md. Trigger on any mention of: threat reporting, security feed, MCP threats, malicious skills, prompt injection reports, IOCs, indicators of compromise, agent security, PromptIntel, MoltThreats, SHIELD.md, or SHIELD.md updates. Also trigger when the agent detects suspicious behavior during normal operation (unexpected tool calls, credential access attempts, unknown MCP servers, exfiltration patterns).

MoltThreats - skill原始代码包