跳至主要内容
小龙虾小龙虾AI
🤖

Apophenia Guard

A cognitive bias interceptor for debugging sessions. Detects when you're seeing patterns that aren't there, chasing red herrings, or letting confirmation bia...

下载55
星标0
版本1.0.0
安全通过

如何使用「Apophenia Guard」？

  1. 打开小龙虾AI（Web 或 iOS App）
  2. 点击上方「立即使用」按钮，或在对话框中输入任务描述
  3. 小龙虾AI 会自动匹配并调用「Apophenia Guard」技能完成任务
  4. 结果即时呈现，支持继续对话优化

相关技能

🤖
Context Guard

防遗忘防卡顿的context管理协议。自动监控水位、分区管理、压缩前存档、压缩后恢复。适用于所有OpenClaw agent和sub-agent。在heartbeat或session启动时触发。

57 下载
🤖
Shadow AI Monitor

Shadow AI Monitor - Enterprise-grade dashboard for tracking employee AI tool usage, data exposure risks, and PIPEDA compliance. Generates professional HTML d...

188 下载
🤖
Mind Security

AI security toolkit — deepfake and AI-generated media detection. Use when verifying if an image, video, or audio is a deepfake or AI-generated.

0 下载
🤖
Vigil

AI agent safety guardrails for tool calls. Use when (1) you want to validate agent tool calls before execution, (2) building agents that run shell commands, file operations, or API calls, (3) adding a safety layer to any MCP server or agent framework, (4) auditing what your agents are doing. Catches destructive commands, SSRF, SQL injection, path traversal, data exfiltration, prompt injection, and credential leaks. Zero dependencies, under 2ms.

623 下载
🤖
Session Guardian

对话永不丢失，任务永不混淆。解决模型掉线、Gateway重启、跨渠道混淆、任务难追踪等痛点。五层防护：增量备份（5分钟）+ 快照（1小时）+ 智能总结（每日）+ 健康检查（6小时）+ 项目管理。v2.0新增：协作链路追踪、智能备份策略、知识库沉淀、协作健康度评分。适用于单agent、多agent协作、团队协作等所...

128 下载
🤖
Shieldcortex

Security framework for AI agents. Enforces instruction gateway control, external action gating, PII protection, sub-agent sandboxing, prompt injection detect...

459 下载