Low severity · published Feb 19, 2026
CVE-2026-24764
OpenClaw has Remote Code Execution via System Prompt Injection in Slack Channel Descriptions
3.7
CVSS
0.2%
EPSS
No
On KEV
Description
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.
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:L/A:N
Attack vector
Network
Complexity
High
Privileges
Low
User interaction
Required
Confidentiality
Low
Integrity
Low
Availability
None
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.2% · higher than 15% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
CL
clawdbot · clawdbot
< 2026.2.3 · source: vendor
OP
Openclaw · Openclaw
before 2026.2.3 · source: NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-24764
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-24764
Patch
https://github.com/openclaw/openclaw/commit/35eb40a7000b59085e9c638a80fd03917c7a095e
Product
https://github.com/openclaw/openclaw/releases/tag/v2026.2.3
Exploit
https://github.com/openclaw/openclaw/security/advisories/GHSA-782p-5fr5-7fj8
More from clawdbot
8.8
CVE-2026-24763
Authenticated Command Injection in OpenClaw Docker Execution via PATH Environment Variable
