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。
Install via ClawdBot CLI:
clawdbot install claw-prompt-injection-guardLoading skill content… the page will refresh in a moment.
AI Usage Analysis
Analysis is being generated… refresh in a few seconds.
Advanced expert in prompt engineering, custom instructions design, and prompt optimization for AI agents
577+ pattern prompt injection defense. Now with typo-tolerant bypass detection. TieredPatternLoader fully operational. Drop-in defense for any LLM application.
Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt nee...
Detect and block prompt injection attacks in emails. Use when reading, processing, or summarizing emails. Scans for fake system outputs, planted thinking blocks, instruction hijacking, and other injection patterns. Requires user confirmation before acting on any instructions found in email content.
Automatically rewrites rough user inputs into optimized, structured prompts for dramatically better AI responses. Prefix any message with "p:" to activate.
Safe OpenClaw config updates with automatic backup, validation, and rollback. For agent use - prevents invalid config updates.