claude-skill-antivirus
Security scanner for Claude Code Skills — 9 engines detect malicious patterns, data exfiltration, dangerous ops across 71K+ skills
No outside reports on file
This tool helps reduce risk but is not a complete security solution; always review what permissions and data access a skill needs before running it, and assume some threats may not be detected.
Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsNo API token requiredLOW
- Package sourcenpm (claude-skill-antivirus)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
npx -y claude-skill-antivirusEverything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-21.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Claude Skill Antivirus
This is a security scanner designed to check AI agent skills (add-on programs) for Claude for malicious code and dangerous behavior. It uses 9 different detection engines to scan over 71,000 skills and looks for patterns like data theft, unsafe operations, and harmful code.
Who it’s for
Developers and teams using Claude Code Skills who want to check whether custom or third-party skills are safe before running them. Security teams that need to audit AI agent code at scale.
Alternatives
- Code review platforms (GitHub advanced security, Semgrep) — static code analysis tools for general code scanning.
- AI safety frameworks (guardrails, Anthropic's safety guidelines) — policy-based controls for AI model outputs.
- Manual security audits — human review of skill source code and behavior.
- Sandboxed execution (Docker, isolated environments) — run untrusted skills in restricted containers.
Setup
Check these steps against the project’s own instructions before running anything.
Install via npm:
npm install claude-skill-antivirus
Then follow the project's README on GitHub for configuration and usage instructions.
Why this grade
Signal-based grade (3/7 points): listed in several sources, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 81
- Weekly npm downloads
- 157
- Listing last refreshed
- 2026-10-30
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Limited verification scope: The tool scans for known malicious patterns, but new or clever attack methods may slip through undetected.
- False confidence: A "safe" result does not guarantee the skill is actually harmless; behavioral exploits or social engineering tricks might bypass detection.
- Supply chain issues: Even vetted skills can be updated with malicious code after initial scanning without your knowledge.
- Data access: Skills can access conversation history, file uploads, and Claude's context unless restricted; the scanner cannot fully prevent data leaks if code is intentionally designed to exfiltrate.
- Obfuscation: Attackers can hide malicious intent using encryption, encoding, or by splitting code across multiple files that the scanner may not fully analyze.
How to lower the risk
Least-privilege permissions
- Grant skills only the minimum permissions they actually need to function.
- Disable access to sensitive file types or conversation history when possible.
Network isolation
- Monitor what external URLs and services a skill tries to connect to.
- Block outbound connections to unknown or suspicious domains.
Monitoring
- Log which skills are used and what data they access over time.
- Review scan results regularly, especially for high-risk or newly updated skills.
Red flags to watch for
- Skills requesting unusual permissions (file system access, network calls) without clear purpose.
- Scanning results that show warnings or low confidence; investigate before using the skill.
Questions
How do I install Claude Skill Antivirus?
Install Claude Skill Antivirus with npm install claude-skill-antivirus or run it directly with npx -y claude-skill-antivirus. For agent integration and configuration flags, see the documentation at github.com/claude-world/claude-skill-antivirus. Pin an exact version and pass --ignore-scripts if you want to block post-install hooks.
Are there security reports about Claude Skill Antivirus?
No reports found for this package in our research (last checked 2026-10-30). Claude Skill Antivirus currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include limited verification scope, false confidence, supply chain issues.
Is Claude Skill Antivirus actively maintained?
Claude Skill Antivirus has 81 GitHub stars and 157 weekly npm downloads. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/claude-world/claude-skill-antivirus before pinning it in production.
What are alternatives to Claude Skill Antivirus?
Notable alternatives to Claude Skill Antivirus include Code review platforms, AI review frameworks, Manual security review (human review of skill source code and behavior), Sandboxed execution. You can also compare Claude Skill Antivirus side by side with other skills in the Related tools section on this page.
README badge and team notes
Maintain or use Claude Skill Antivirus? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/claude-world-claude-skill-antivirus)HTML embed:
<a href="https://agentarmorhq.com/skills/claude-world-claude-skill-antivirus"><img src="https://agentarmorhq.com/api/badge/claude-world-claude-skill-antivirus" alt="AgentArmorHQ Risk Grade for Claude Skill Antivirus" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "claude-world-claude-skill-antivirus"- Compare Claude Skill Antivirus →
- Add to a team allowlist
- Claude and terminal guide →
- Download the PDF guide
Share with your security lead
Need sign-off to use claude-skill-antivirus? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: claude-skill-antivirus
- **Listing URL:** https://agentarmorhq.com/skills/claude-world-claude-skill-antivirus
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 81 GitHub stars, 157 weekly npm downloads
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** npm (claude-skill-antivirus)
#### Recommended Hardened Setup
- **Command:** `npx -y --ignore-scripts claude-skill-antivirus`
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- claude-world
- Source code
- github.com/claude-world/claude-skill-antivirus
- Install command
- npm install claude-skill-antivirus
- Est. context load
- ~62 tokens idle · ~450 tokens when active (on-demand skill)
- Popularity
- 81 GitHub stars, 157 weekly npm downloads
- Last updated
- 2026-10-30
- Last graded
- 2026-10-21
Community
Discussions for Claude Skill Antivirus
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude