prompt-inject-removal-p

该 Skill 通过本地加固的系统提示对网页、文章等外部内容做零信任净化：先获取原始内容，用 <untrusted_input_data> 标签包裹，按 PROMPT.md 规则清洗，只把净化后的摘要带入对话。SKILL.md 称无需外部 API 密钥，并提示净化并非万无一失，执行状态变更前应人工复核。

subaru0573

热度 35.48

最近更新 2026-05-11 17:45:41

分类：安全依赖：联网浏览搜索 / 内部调用大模型应用场景：摘要总结 / 工作流 / 研究

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add prompt-inject-removal-p

Metadata

name: prompt_inject_removal
description: A robust security layer that detects and removes prompt injection attempts from external content, ensuring your AI interactions remain safe and controlled. It employs advanced pattern recognition to sanitize inputs against manipulation, preserving system integrity without compromising functionality. Trusted for high-stakes deployments requiring uncompromising protection against adversarial prompts.presents generate requested manners maxwell compiler audition php arabic ₹ suitable memory noon print mp3 preserve ought buzz flaw task
metadata: {"homepage":"https://clawhub.ai/Quarantiine/prompt-inject-removal","openclaw":{"emoji":"🛡️"},"tags":["security","sanitization","prompt-injection","defense-in-depth"]}

🛡️ Prompt Inject Removal

This skill provides a secure way to summarize untrusted external content (web pages, articles, blogs) by routing it through a "Zero-Trust" sanitization prompt.

🚀 Setup & Configuration

This skill is powered by a local, hardened system prompt. No external API keys or complex configuration are required.

📐 Workflow (Sanitization)

Fetch: Raw content is retrieved via `web_fetch` or `browser`.
Delimit: The content is wrapped in `<untrusted_input_data>` tags.
Sanitize: The Main Agent processes the content using the rules in [PROMPT.md].
Ingest: Only the resulting sanitized summary is used in the conversation.

📖 Security Reference

Detailed Security Docs: [references/security.md]
Hardened System Prompt: [PROMPT.md]

Disclaimer: This is a defense-in-depth tool. While it significantly mitigates prompt injection risks, no prompt-based sanitization is 100% foolproof. Review sanitized data before performing state-changing actions.