FindSkills

claw-prompt-injection-guard

防护间接提示词注入攻击(Indirect Prompt Injection)。当处理网页内容、搜索结果、邮件、社交媒体等外部来源信息时触发。用于识别和防范外部内容中隐藏的恶意指令。所有 Claw 都应安装此技能。

by clawhub community Source: clawhub
Quality: medium Safety: community Category: AI & ML Updated: 2026-03-10
View on ClawHub JSON API

Related Skills in AI & ML

"stock_analyzer"
LLM驱动的 A/H/美股智能分析器,多数据源行情 + 实时新闻 + Gemini 决策仪表盘 + 多渠道推送,零成本,纯白嫖,定时运行
claudeception
A Claude Code skill for autonomous skill extraction and continuous learning. Hav...
claw-compactor
🦞 Claw Compactor — The 98% Crusher. Cut your AI agent token spend in half with ...
pensieve
tore your decisions and principles. Claude reads them to make better choices.
vuln-analysis-expert
wooyun-legacy skill for claude code
frontend-slides
Create beautiful slides on the web using Claude's frontend skills

View all AI & ML skills