CVE-2026-24764
February 19, 2026
OpenClaw (formerly Clawdbot) is a personal AI assistant users run on their own devices. In versions 2026.2.2 and below, when the Slack integration is enabled, channel metadata (topic/description) can be incorporated into the model's system prompt. Prompt injection is a documented risk for LLM-driven systems. This issue increases the injection surface by allowing untrusted Slack channel metadata to be treated as higher-trust system input. This issue has been fixed in version 2026.2.3.
Affected Packages
https://github.com/openclaw/openclaw.git (GITHUB):
Affected version(s) >=v0.1.0 <v2026.2.3Fix Suggestion:
Update to version v2026.2.3openclaw (NPM):
Affected version(s) >=0.0.1 <2026.2.3Fix Suggestion:
Update to version 2026.2.3Related Resources (5)
Do you need more information?
Contact UsCVSS v4
Base Score:
2.1
Attack Vector
NETWORK
Attack Complexity
HIGH
Attack Requirements
NONE
Privileges Required
LOW
User Interaction
PASSIVE
Vulnerable System Confidentiality
LOW
Vulnerable System Integrity
LOW
Vulnerable System Availability
NONE
Subsequent System Confidentiality
NONE
Subsequent System Integrity
NONE
Subsequent System Availability
NONE
CVSS v3
Base Score:
3.7
Attack Vector
NETWORK
Attack Complexity
HIGH
Privileges Required
LOW
User Interaction
REQUIRED
Scope
UNCHANGED
Confidentiality
LOW
Integrity
LOW
Availability
NONE
Weakness Type (CWE)
EPSS
Base Score:
0.03
