Teycir/SkillsGuard
Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts before they run.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/Teycir/SkillsGuard MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit <redacted>-dynamic-imports-10 .claude/skills/borderline-dynamic-imports-10 $ npx degit <redacted>-dynamic-imports-16 .claude/skills/borderline-dynamic-imports-16 $ npx degit <redacted>-dynamic-imports-22 .claude/skills/borderline-dynamic-imports-22 $ npx degit <redacted>-dynamic-imports-4 .claude/skills/borderline-dynamic-imports-4 $ npx degit <redacted>-env-access-11 .claude/skills/borderline-env-access-11 $ npx degit <redacted>-env-access-17 .claude/skills/borderline-env-access-17 $ npx degit <redacted>-env-access-23 .claude/skills/borderline-env-access-23 $ npx degit <redacted>-env-access-5 .claude/skills/borderline-env-access-5 $ npx degit <redacted>-eval-usage-15 .claude/skills/borderline-eval-usage-15 $ npx degit <redacted>-eval-usage-21 .claude/skills/borderline-eval-usage-21 $ npx degit <redacted>-eval-usage-3 .claude/skills/borderline-eval-usage-3 $ npx degit <redacted>-eval-usage-9 .claude/skills/borderline-eval-usage-9 $ npx degit <redacted>-file-operations-1 .claude/skills/borderline-file-operations-1 $ npx degit <redacted>-file-operations-13 .claude/skills/borderline-file-operations-13 $ npx degit <redacted>-file-operations-19 .claude/skills/borderline-file-operations-19 $ npx degit <redacted>-file-operations-25 .claude/skills/borderline-file-operations-25 $ npx degit <redacted>-file-operations-7 .claude/skills/borderline-file-operations-7 $ npx degit <redacted>-network-calls-12 .claude/skills/borderline-network-calls-12 $ npx degit <redacted>-network-calls-18 .claude/skills/borderline-network-calls-18 $ npx degit <redacted>-network-calls-24 .claude/skills/borderline-network-calls-24 $ npx degit <redacted>-network-calls-6 .claude/skills/borderline-network-calls-6 $ npx degit <redacted>-process-spawn-14 .claude/skills/borderline-process-spawn-14 $ npx degit <redacted>-process-spawn-2 .claude/skills/borderline-process-spawn-2 $ npx degit <redacted>-process-spawn-20 .claude/skills/borderline-process-spawn-20 $ npx degit <redacted>-process-spawn-8 .claude/skills/borderline-process-spawn-8 $ npx degit <redacted>-command-injection-14 .claude/skills/malicious-command-injection-14 $ npx degit <redacted>-command-injection-2 .claude/skills/malicious-command-injection-2 $ npx degit <redacted>-command-injection-8 .claude/skills/malicious-command-injection-8 $ npx degit <redacted>-exfiltration-1 .claude/skills/malicious-exfiltration-1 $ npx degit <redacted>-exfiltration-13 .claude/skills/malicious-exfiltration-13 $ npx degit <redacted>-exfiltration-7 .claude/skills/malicious-exfiltration-7 $ npx degit <redacted>-obfuscation-10 .claude/skills/malicious-obfuscation-10 $ npx degit <redacted>-obfuscation-4 .claude/skills/malicious-obfuscation-4 $ npx degit <redacted>-privilege-escalation-15 .claude/skills/malicious-privilege-escalation-15 $ npx degit <redacted>-privilege-escalation-3 .claude/skills/malicious-privilege-escalation-3 $ npx degit <redacted>-privilege-escalation-9 .claude/skills/malicious-privilege-escalation-9 $ npx degit <redacted>-prompt-injection-12 .claude/skills/malicious-prompt-injection-12 $ npx degit <redacted>-prompt-injection-6 .claude/skills/malicious-prompt-injection-6 $ npx degit <redacted>-supply-chain-11 .claude/skills/malicious-supply-chain-11 $ npx degit <redacted>-supply-chain-5 .claude/skills/malicious-supply-chain-5
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (100)
borderline-dynamic-imports-10borderline-dynamic-imports-16borderline-dynamic-imports-22borderline-dynamic-imports-4borderline-env-access-11borderline-env-access-17borderline-env-access-23borderline-env-access-5borderline-eval-usage-15borderline-eval-usage-21borderline-eval-usage-3borderline-eval-usage-9borderline-file-operations-1borderline-file-operations-13borderline-file-operations-19borderline-file-operations-25borderline-file-operations-7borderline-network-calls-12borderline-network-calls-18borderline-network-calls-24borderline-network-calls-6borderline-process-spawn-14borderline-process-spawn-2borderline-process-spawn-20borderline-process-spawn-8malicious-command-injection-14malicious-command-injection-2malicious-command-injection-8malicious-exfiltration-1malicious-exfiltration-13malicious-exfiltration-7malicious-obfuscation-10malicious-obfuscation-4malicious-privilege-escalation-15malicious-privilege-escalation-3malicious-privilege-escalation-9malicious-prompt-injection-12malicious-prompt-injection-6malicious-supply-chain-11malicious-supply-chain-5safe-backend-21safe-backend-33safe-backend-45safe-backend-57safe-backend-9safe-code-review-12safe-code-review-24safe-code-review-36safe-code-review-48safe-code-review-60safe-database-10safe-database-22safe-database-34safe-database-46safe-database-58safe-debugging-17safe-debugging-29safe-debugging-41safe-debugging-5safe-debugging-53safe-deployment-11safe-deployment-23safe-deployment-35safe-deployment-47safe-deployment-59safe-documentation-15safe-documentation-27safe-documentation-3safe-documentation-39safe-documentation-51safe-frontend-20safe-frontend-32safe-frontend-44safe-frontend-56safe-frontend-8safe-git-workflow-1safe-git-workflow-13safe-git-workflow-25safe-git-workflow-37safe-git-workflow-49safe-performance-18safe-performance-30safe-performance-42safe-performance-54safe-performance-6safe-refactoring-16safe-refactoring-28safe-refactoring-4safe-refactoring-40safe-refactoring-52safe-security-audit-19safe-security-audit-31safe-security-audit-43safe-security-audit-55safe-security-audit-7safe-testing-14safe-testing-2safe-testing-26safe-testing-38safe-testing-50
Similar rigs
obra/superpowers
An agentic skills framework & software development methodology that works.
Skill Collector 3.0k tok ·
anthropics/skills
Public repository for Agent Skills
Skill Collector 1.3k tok ·
anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Skill Collector 1.4k tok ·
JuliusBrussee/caveman
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Skill Collector 16.5k tok ·