SkillGuard · by SameDayDesk

Scan a Claude Code skill or MCP server for malware before you install it.

The skill/MCP ecosystem is exploding — and so is the attack surface. SkillGuard statically scans any skill, plugin, or MCP server for the patterns attackers actually use, in seconds. Free, no signup, and it never runs the code it's inspecting.

npx github:epistemedeus/skillguard https://github.com/owner/repo
71malicious skills found in the wild
26%of published skills carry vulnerabilities
30+MCP CVEs in 60 days

What it catches

DANGER (4)
  SKILL.md
    ■ Prompt-injection / data-exfil instruction in text     [prompt-injection]
  index.js
    ■ Env/secret exfiltration (sensitive env var + network) [env-exfil]
    ■ Hardcoded webhook / pastebin / raw-IP endpoint        [exfil-host]
    ■ Obfuscated exec: eval(atob), curl | bash              [obfuscation]

✗ DANGEROUS — do NOT install without reviewing the flagged files.

Also detects committed binaries, hardcoded private keys, the "commit an encrypted artifact" honeypot pattern, install-time postinstall hooks, and auto-approve-all / --dangerously-skip-permissions configs. Exit codes (0/2/3) let you gate CI on it. Source on GitHub →

Stop worrying about what you install

The free CLI is the first line of defense. If you pull in third-party skills and MCP servers regularly, we'll do the deeper work for you:

Deep audit

$29 one-time
  • A human review of one skill / MCP / plugin you're about to depend on
  • Written risk report with specific findings + a go / no-go
  • Delivered same day
Get a deep audit · $29

Watch mode

$12 / month
  • We re-scan the skills + MCP servers you depend on on every upstream release
  • Alert the moment new risk appears (the rug-pull / mutable-tool problem)
  • Cancel anytime
Start watching · $12/mo

Safe by design

SkillGuard does static analysis only. It clones with git clone (hooks disabled) and reads files — it never runs npm install, never executes build/postinstall scripts, and never runs the target code. Scanning a malicious package can't harm you. (A scanner that executed what it inspects would be the very risk it's meant to prevent.)

Heuristics catch known-bad patterns; a novel, determined attack can evade any static scanner. SkillGuard is a fast first line of defense, not a guarantee.