Prompt Injection Removal

该 Skill 定义了一条零信任净化流程：用 web_fetch 或 browser 抓取外部网页、文章等不可信内容，包裹在 <untrusted_input_data> 标签中，交给主 Agent 按 PROMPT.md 的加固提示规则处理，最终只用净化后的摘要进入会话。材料声明无需外部 API Key，并提示提示词防护并非万无一失，执行状态变更操作前仍需人工复核。

quarantiine

热度 86.11

最近更新 2026-05-11 17:27:50

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 / 数据处理

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

Metadata

name: prompt_inject_removal
description: A secure sanitization system to strip instructions from external content.
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.