Ruflo Aidefence
插件 已验证 活跃AI safety scanning, PII detection, prompt injection defense, and adaptive threat learning
To enhance AI system security by proactively detecting and defending against threats like prompt injection, PII leaks, and adversarial content.
功能
- AI safety scanning for adversarial content
- PII detection and flagging
- Prompt injection defense
- Adaptive threat learning
- Threat classification with confidence scores
使用场景
- Scanning user inputs before processing to prevent prompt injection
- Detecting PII in code or data before committing or storing
- Classifying and learning from detected security threats
- Implementing a defense-in-depth strategy for AI systems
非目标
- Performing destructive operations
- Replacing core AI model safety features
- Acting as a general-purpose security scanner for code vulnerabilities
Documentation
- info:Configuration & parameter referenceThe README mentions commands and skills but does not detail specific parameters or default values for the tools.
安装
请先添加 Marketplace
/plugin marketplace add ruvnet/ruflo/plugin install ruflo-aidefence@ruflo质量评分
已验证类似扩展
Cc Safe Setup
99734 个用于 Claude Code 的安全钩子 — 在自主 AI 编码会话期间防止文件删除、凭证泄露、git 灾难和令牌浪费
Claude Code Hooks
99为 Claude Code 的自动化运行提供生产环境安全钩子。包括上下文监控、语法检查、分支保护、活动日志记录等。
Hooks Safety
99Essential safety hooks to prevent destructive operations in Claude Code. From cc-safe-setup (655+ hooks).
Cc Safe Setup
97Claude Code 的 Token 消耗防护。警告大型文件读取（100KB+），限制每个会话的唯一文件读取次数，估算 Token 预算，并限制子代理生成。基于 800+ 小时的自主运行数据。
Cc Safe Setup
97Claude Code 的 5 个基本安全钩子。阻止 rm -rf、force-push、hard-reset、.env 覆盖和 package publish。来自 800 多个小时自主运行的最低可行安全网。
Msapps Sosa Governor
95SOSA governance engine — enforce supervision policies, trust gradients, and capability boundaries on AI agent actions in real time