RCE in Anthropic Claude_code
CVE-2025-54795
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 th…
Vulnerability class: Command Injection (OS Command Injection)
EPSS: 0.010 (58.0th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 9.8 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H.
Affected products
- Anthropic Claude_code
- Anthropics Claude-code — versions < 1.0.20
Weakness classification (CWE)
Public proof-of-concept exploits
References
- security-advisories@github.com (x_refsource_CONFIRM, Vendor Advisory)
Frequently asked questions
- What is CVE-2025-54795?
- CVE-2025-54795 is a critical-severity vulnerability in Anthropic Claude_code, classified under OS Command Injection. CVSS score: 9.8/10. Published 2025-08-05.
- How severe is CVE-2025-54795?
- Critical severity. CVSS v3 base score is 9.8 out of 10.
- Is CVE-2025-54795 known to be exploited?
- 4 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.