跳到正文
TakoAPI
返回技能列表

aegis-shield

由 deegerwalker 提供

Web & Frontend Development
688下载量由 clawskills.sh 提供
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Prompt-injection and data-exfiltration screening for untrusted text.

描述

该技能的功能

Screens untrusted text for prompt injection, data exfiltration, and tool-abuse patterns before it reaches memory or other tools. Assigns a severity score and routes content to either acceptance or quarantine. Includes a safe memory append workflow that enforces scan and lint checks before any write.

Intercepts malicious content at the boundary rather than relying on downstream tools to handle hostile input safely.

何时使用

  • Scanning email content before summarizing it to an agent
  • Screening scraped web pages before feeding them into a pipeline
  • Quarantining social media replies that contain suspicious instructions
  • Enforcing sanitized memory writes when processing user-supplied input
  • Blocking exfiltration attempts hidden in LLM-targeted document payloads

示例工作流

输入

User asks: scan this webpage content before summarizing it

智能体
  1. 1

    Pass the raw fetched text to the scan step

  2. 2

    Receive severity score and flag list from the scanner

  3. 3

    Check if severity is medium or higher

  4. 4

    If severity is medium+, route content to quarantine and halt pipeline

  5. 5

    If severity is low, proceed to summarize the sanitized text

输出

Content is either quarantined with a report or cleared for downstream use

安装

clawhub install deegerwalker/aegis-shield

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接