Skip to content

CVE-2026-24764 OpenClaw has Remote Code Execution via System Prompt Injection in Slack Channel Descriptions

LowCVSS 3.7 EPSS 0.24%
Published
Updated
Exploit status
No public exploit known
CISA SSVC
No known exploitation · automatable: no · technical impact: partial

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.

Upgrade path

3 packages: 2 fixed.

PackageAffectedFixed inStatus
npm openclaw(npm) < 2026.2.3 2026.2.3 Fixed
openclaw < 2026.2.3 2026.2.3 Fixed
clawdbot = < 2026.2.3 No fix listed Versions listed

Affected products

ProductAffected versionsFixed in
clawdbot = < 2026.2.3 No fix listed
npm openclaw(npm) < 2026.2.3 2026.2.3
openclaw < 2026.2.3 2026.2.3

References