CVE-2025-54795: anthropic claude_code OS Command Injection
Vulnerability summary
CVE-2025-54795 is a critical (CVSS 9.8) OS Command Injection vulnerability in anthropic claude_code. EPSS estimates a 1.00% chance of exploitation in the next 30 days, higher than 62.5% of scored vulnerabilities.
Timeline
- 05-08-2025PublishedVulnerability first disclosed.
- 05-08-2025Last modifiedVulnerability information updated.
Description
Claude Code is an agentic coding tool. In versions below 1.0.20, an error in command parsing makes it possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. This is fixed in version 1.0.20.
CVSS metrics
4 scores · 3 sources · 2 versions- OSV · NpmEcosystem advisory · calculated8.7HighCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
- NVDNIST8.7HighCVSS:4.0/AV:N/AC:L/AT:N/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
1.00%
Chance of exploitation in the next 30 days
Percentile
63%
Versus all other CVEs
30-day change
0.00 pp
From 1.00% 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 causeAffected systems
@anthropic-ai1 product
- claude-code< 1.0.20
Anthropic1 product
- claude_code< 1.0.20
Anthropics1 product
- claude-code< 1.0.20
3 vendors · 3 products
References
3 links- github.com/anthropics/claude-code/security/advisories/GHSA-x56v-x2h6-7j34X Refsource CONFIRMWEBVendor Advisory