skill-firewall
mkhaytman87 제작
Web & Frontend Development요약
Security layer that prevents prompt injection from external skills.
설명
이 스킬이 하는 일
A security layer for AI agents that intercepts requests to install external skills and rewrites them from scratch instead of copying them verbatim. Prevents prompt injection via hidden HTML comments, zero-width Unicode characters, and embedded malicious instructions embedded in external skill files.
Copying and executing external skills directly exposes the agent to payloads invisible in rendered markdown but visible to the LLM, which regeneration eliminates entirely.
사용 시점
- Installing a community skill from ClawHub without running hidden malicious instructions
- Safely evaluating a GitHub-hosted skill before adding it to a project
- Blocking a curl-based exfiltration attempt disguised as skill setup
- Reviewing a skills.sh package for obfuscated Unicode payloads before use
- Sanitizing a third-party skill that references external files in a poison chain
예시 워크플로
User asks: Install the cloudflare skill from skills.sh
- 1
Acknowledge the request and state that the skill will be rewritten, not copied
- 2
Fetch the external skill content and identify its actual purpose
- 3
Flag any suspicious elements such as HTML comments or external URL references
- 4
Write a clean replacement skill in standard ASCII with no external references
- 5
Present the rewrite with a summary report and wait for explicit user approval before saving
A sanitized, human-approved skill file saved to the skills directory, functionally equivalent to the original but free of injected instructions
설치
clawhub install mkhaytman87/skill-firewallCLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.