Vulnerability · Published Sep 2, 2026 · Assigned by VulnCheck
CVE-2026-84810claude-skill-antivirus Analysis Bypass via Manifest-Only Local Directory Scan
Medium 6.5
In plain English
A medium-severity security flaw in claude-skill-antivirus from claude-world. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 41% of all known vulnerabilities).
Official description
claude-skill-antivirus fails to analyze executable files when scanning local skill directories, reading only SKILL.md while ignoring Python source, bytecode, and other artifacts in the scripts directory. Attackers can distribute skills with malicious code in non-manifest files that receive a SAFE verdict with 100/100 trust score despite containing unanalyzed executable payloads.
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| claude-world | claude-skill-antivirus | 0 – through 2.1.3 |
Weakness: CWE-693 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:H/A:N
References
- GitHub Issue #33 issue-tracking
- https://github.com/claude-world/claude-skill-antivirus/blob/v2.1.3/src/utils/downloader.js technical-description
- https://github.com/claude-world/claude-skill-antivirus/blob/v2.1.3/src/scanner/index.js technical-description
- https://github.com/claude-world/claude-skill-antivirus product
- VulnCheck Advisory: claude-skill-antivirus Analysis Bypass via Manifest-Only Local Directory Scan third-party-advisory
- https://github.com/nedlir/skills-scanner-bypass exploit