GHSA-qgqw-h4xq-7w8w
Suggest an improvement- Source
- https://github.com/advisories/GHSA-qgqw-h4xq-7w8w
- Import Source
- https://github.com/github/advisory-database/blob/main/advisories/github-reviewed/2026/02/GHSA-qgqw-h4xq-7w8w/GHSA-qgqw-h4xq-7w8w.json
- JSON Data
- https://api.osv.dev/v1/vulns/GHSA-qgqw-h4xq-7w8w
- Aliases
-
- CVE-2026-24887
- Published
- 2026-02-03T19:33:32Z
- Modified
- 2026-02-03T22:34:25.261494Z
- Severity
-
- 7.7 (High) CVSS_V4 - CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N CVSS Calculator
- Summary
- Claude Code has a Command Injection in find Command Bypasses User Approval Prompt
- Details
-
Due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window.
Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to the latest version.
Claude Code thanks https://hackerone.com/alexbernier for reporting this issue!
- Database specific
{ "cwe_ids": [ "CWE-78", "CWE-94" ], "severity": "HIGH", "github_reviewed_at": "2026-02-03T19:33:32Z", "github_reviewed": true, "nvd_published_at": "2026-02-03T21:16:13Z" }- References
Affected packages
npm / @anthropic-ai/claude-code
Package
- Name
- @anthropic-ai/claude-code
- View open source insights on deps.dev
- Purl
- pkg:npm/%40anthropic-ai/claude-code