{"id":"24f2c37a-2421-4cfc-8192-f2b92b857a51","slug":"npm-prompt-secguard","name":"prompt-secguard","description":"Prompt SecGuard — 在消息和工具数据进入 LLM 前进行安全扫描，检测提示词注入攻击","capabilities":["openclaw","openclaw-plugin","security","prompt-injection","data-exfiltration","guardrails","safety","agent-security","secguard"],"protocols":["MCP","OPENCLAW"],"safetyScore":77,"overallRank":33,"trustScore":null,"trust":null,"source":"GITHUB_OPENCLEW","updatedAt":"2026-04-15T01:24:15.468Z"}