k7-total-security-unlock-patch-detection — Claude Code security skill
k7-total-security-unlock-patch-detection scores a repository that advertises cracks or patches for antivirus software and lists the red flags pointing to malware distribution.
no license 117 installs ★ 13 updated 2026-10-09
npx skills add reason-machines/security-skills --skill k7-total-security-unlock-patch-detection -a claude-codeWhat k7-total-security-unlock-patch-detection does
The skill fires when you hand the agent a repository selling an unlock patch, keygen or crack for antivirus software. Two Python functions do the work. One takes GitHub metadata and adds points for crack wording in the description or topics, HTML listed as the primary language, a missing license, more than 100 stars with no forks, and a creation date set in the future. The other reads the README and flags downloads that lead off GitHub, fetch commands piped straight into a shell, and a license disclaimer that contradicts itself.
Points add up to a score out of 100, and the is_malicious flag turns on at 50. Anything below lands in MEDIUM and passes. Neither function opens the repository's files; both work from metadata and README text, so a tidy page with no outward marks slips through.
Both routines are written in Python. You supply the inputs yourself: a metadata dict from the GitHub API and the raw README contents.
What it helps with
- vet a repo offering an antivirus crack before downloading anything from it
- write down why a repository looks fake, point by point
- catch download links that bypass GitHub releases
- tell inflated stars apart from real interest in a project
- gather indicators for a phishing report
Example prompts for the agent
- Check the repo
K7-Total-Security-Unlock-Patch-16-0-1195and tell me whether it ships malware or a real patch. - Go through this README and list the red flags you find.
- Score this suspicious unlock-patch repository from its metadata.
How to install k7-total-security-unlock-patch-detection
1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill k7-total-security-unlock-patch-detection -a claude-code2Manually: put the files in place
~/.claude/skills/k7-total-security-unlock-patch-detection/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/k7-total-security-unlock-patch-detection/
1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill k7-total-security-unlock-patch-detection -a codex2Manually: put the files in place
.agents/skills/k7-total-security-unlock-patch-detection/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill k7-total-security-unlock-patch-detection -a cursor2Manually: put the files in place
.cursor/skills/k7-total-security-unlock-patch-detection/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/security-skills skills/k7-total-security-unlock-patch-detection2Manually: put the files in place
.github/skills/k7-total-security-unlock-patch-detection/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill k7-total-security-unlock-patch-detection -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/security-skills --path skills/k7-total-security-unlock-patch-detectionManually: put the files in place
.devin/skills/k7-total-security-unlock-patch-detection/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/security-skills --skill k7-total-security-unlock-patch-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 k7-total-security-unlock-patch-detection
How do I install k7-total-security-unlock-patch-detection in Claude Code?
Run npx skills add reason-machines/security-skills --skill k7-total-security-unlock-patch-detection -a claude-code. The skill file lands at ~/.claude/skills/k7-total-security-unlock-patch-detection/SKILL.md.
What does this skill do?
It helps an agent recognise a repository that pushes malicious code under the guise of an antivirus patch or crack, and shows the reasoning behind the verdict.
What pushes the score past the threshold?
Crack keywords in the description or topics, HTML as the primary language, no license, plenty of stars with no forks, a creation date in the future, plus off-site download links and odd shell commands in the README. The cutoff sits at 50 out of 100.