Summary
This is a pre-install security auditor that flags suspicious network behavior before you run untrusted skills. It scans for red flags like connections to raw IPs, DNS tunneling, exfiltration patterns where code reads files then POSTs them somewhere, and endpoints that weren't declared upfront. The real value is catching skills that request both file read and network permissions, which is the classic setup for stealing your .env or source code. It won't run the skill itself, just static analysis of what it declares and what patterns show up in the code. If you're installing community skills or anything from outside your org, this catches the obvious data theft attempts before they happen.
Install to Claude Code
npx -y skills add useai-pro/openclaw-skills-security --skill network-watcher --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
