fort-firewall-malware-repository-detection — Claude Code skill
fort-firewall-malware-repository-detection scores repositories that pretend to be firewall or security tools and flags the ones pushing cracks, fake activators and redirect downloads.
no license 128 installs ★ 13 updated 2026-10-09
npx skills add reason-machines/security-skills --skill fort-firewall-malware-repository-detection -a claude-codeWhat fort-firewall-malware-repository-detection does
This skill gives a coding agent a procedure for taking apart repositories that pose as security software while shipping infected installers or activation bypasses. The core is a keyword checklist plus a small Python scorer you feed repository metadata.
Points come from piracy words in topics, README lines about switching off antivirus or dodging activation, links to github.io pages, shorteners and file hosts, a missing Releases section next to a download call to action, and creation dates set in the future. Past 60 points the verdict flips to malicious; 100 and up is CRITICAL.
Nothing is fetched for you. Topics, README text and creation date have to be collected first — gh repo view --json topics and a read-only git clone will do, and the instructions are explicit that nothing from the clone gets executed. Matching is word-based, so a real project that mentions false positives also picks up points; check which rules fired before trusting the total.
What it helps with
- vet a repository before anyone downloads its installer
- spot README wording that tells users to disable antivirus
- tell official GitHub Releases from a
github.ioredirect - explain to a teammate why a download link is dangerous
- check whether a security repo is just keyword spam
Example prompts for the agent
- Check this repo for malware distribution signals and show me the score.
- Read the topics and README of
fort-firewall-security-fixand tell me if it is safe to download from. - Are the download links in this README official releases or a redirect?
How to install fort-firewall-malware-repository-detection
1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill fort-firewall-malware-repository-detection -a claude-code2Manually: put the files in place
~/.claude/skills/fort-firewall-malware-repository-detection/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/fort-firewall-malware-repository-detection/
1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill fort-firewall-malware-repository-detection -a codex2Manually: put the files in place
.agents/skills/fort-firewall-malware-repository-detection/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill fort-firewall-malware-repository-detection -a cursor2Manually: put the files in place
.cursor/skills/fort-firewall-malware-repository-detection/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/security-skills skills/fort-firewall-malware-repository-detection2Manually: put the files in place
.github/skills/fort-firewall-malware-repository-detection/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill fort-firewall-malware-repository-detection -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/security-skills --path skills/fort-firewall-malware-repository-detectionManually: put the files in place
.devin/skills/fort-firewall-malware-repository-detection/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill fort-firewall-malware-repository-detection -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about fort-firewall-malware-repository-detection
How do I install fort-firewall-malware-repository-detection in Claude Code?
Run npx skills add reason-machines/security-skills --skill fort-firewall-malware-repository-detection -a claude-code, then the skill sits at ~/.claude/skills/fort-firewall-malware-repository-detection/SKILL.md.
What does this skill actually check?
Topics, README phrases, download link patterns and the creation date go into one score, and the score maps to a threat level from LOW to CRITICAL.
Does it pull the repository data itself?
No. You gather the topics, README and date first and pass them to the scorer, so the analysis works on what you hand it.