OpenClaw is a personal AI assistant. In versions 2026.2.13 and below, when using macOS, the Claude CLI keychain credential refresh path constructed a shell command to write the updated JSON blob into Keychain via security add-generic-password -w .... Because OAuth tokens are user-controlled data, this created an OS command injection risk.
This issue has been fixed in version 2026.2.14.
Attack Parameters
Attack Vector
Network
Can be exploited remotely
Attack Complexity
Low
Easy to exploit
Privileges Required
Low
Basic privileges needed
User Interaction
Required
User action required
Impact Assessment
Confidentiality
High
Complete data leak
Integrity
High
Complete data modification
Availability
Low
Partial disruption
CVSS Vector v3.1
Weakness Type (CWE)
References 6
https://github.com/openclaw/openclaw/commit/66d7178f2d6f9d60abad35797f97f3e6138…
security-advisories@github.com
https://github.com/openclaw/openclaw/commit/9dce3d8bf83f13c067bc3c32291643d2f1f…
security-advisories@github.com
https://github.com/openclaw/openclaw/commit/b908388245764fb3586859f44d1dff5372b…
security-advisories@github.com
https://github.com/openclaw/openclaw/pull/15924
security-advisories@github.com
https://github.com/openclaw/openclaw/releases/tag/v2026.2.14
security-advisories@github.com
https://github.com/openclaw/openclaw/security/advisories/GHSA-4564-pvr2-qq4h
security-advisories@github.com