CVE-2026-25723: anthropic claude_code Improper Input Validation
Vulnerability summary
CVE-2026-25723 is a high (CVSS 7.7) Improper Input Validation vulnerability in anthropic claude_code. EPSS estimates a 0.53% chance of exploitation in the next 30 days, higher than 43.9% of scored vulnerabilities.
Timeline
- 06-02-2026PublishedVulnerability first disclosed.
- 06-02-2026Last modifiedVulnerability information updated.
Description
Claude Code is an agentic coding tool. Prior to version 2.0.55, Claude Code failed to properly validate commands using piped sed operations with the echo command, allowing attackers to bypass file write restrictions. This vulnerability enabled writing to sensitive directories like the .claude folder and paths outside the project scope. Exploiting this required the ability to execute commands through Claude Code with the "accept edits" feature enabled. This issue has been patched in version 2.0.55.
CVSS metrics
4 scores · 3 sources · 2 versions- OSV · NpmEcosystem advisory · calculated7.7HighCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
- NVDNIST7.7HighCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
EPSS trend
Probability
0.53%
Chance of exploitation in the next 30 days
Percentile
44%
Versus all other CVEs
30-day change
+0.26 pp
From 0.27% on 21-09-2026
Known exploited
Compare KEV catalogsNot in any of the 3 tracked catalogs.
Public exploits
0 foundNo public exploits indexed.
Weaknesses
CWE · root cause- CWE-20Improper Input ValidationThe product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly.
- CWE-78Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component.
Affected systems
@anthropic-ai1 product
- claude-code< 2.0.55
Anthropic1 product
- claude_code< 2.0.55
Anthropics1 product
- claude-code< 2.0.55
3 vendors · 3 products
References
3 links- github.com/anthropics/claude-code/security/advisories/GHSA-mhg7-666j-cqg4X Refsource CONFIRMWEBVendor Advisory