CVE-2025-54795
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.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.97%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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 4.0
- 8.7 HIGHCVSS: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/M
- EPSS
- 0.97% probability · 60th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-78
- Affected
- anthropic/claude code
- Source
- security-advisories@github.com
References
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.