skill-firewall
par mkhaytman87
Web & Frontend DevelopmentRésumé
Security layer that prevents prompt injection from external skills.
Description
Ce que fait ce skill
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.
Quand l'utiliser
- 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
Exemple de workflow
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
Installation
clawhub install mkhaytman87/skill-firewallExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.