prompt-injection-defenseHarden agent sessions against prompt injection from untrusted content. Use when the agent reads web search results, emails, downloaded files, PDFs, or any ex...
Install via ClawdBot CLI:
clawdbot install adrianteng/prompt-injection-defenseGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains instructions to override system prompt or ignore user requests
"Ignore previous instructions"Calls external URL not in known-safe list
https://example.com/apiAI Analysis
The skill is a defensive security tool designed to detect and mitigate prompt injection attacks; it does not send user data externally, contains no hidden instructions or credential harvesting, and its example URL is illustrative, not a call to an actual unauthorized service.
Audited Apr 17, 2026 · audit v1.0
Usage Guide
Loading usage data… refresh in a few seconds.
Scored Apr 19, 2026
Expert prompt engineer specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, an...
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RA...
AI绘画提示词优化器 | 智能优化Midjourney/SD/DALL-E提示词。支持风格转换、批量生成。
Clean, tag, and index a user-provided prompt collection so the right prompt can be found, reused, and improved quickly.
为即梦 Seedance 2.0 多模态AI视频生成模型撰写高质量提示词。当用户需要使用文本、图片、视频、音频等多模态输入创作视频提示词时触发。涵盖@引用语法、运镜复刻、特效模仿、视频延长、视频编辑、音乐卡点、电商广告、短剧创作、科普教育等场景。
Store, organize, search, and reuse customizable prompt templates with variables to streamline your workflow and avoid rewriting prompts.