Skip to content
OpenAdvisories
Low · 3.7 CVE-2026-24764 EUVD-2026-8120GHSA-782p-5fr5-7fj8

OpenClaw has Remote Code Execution via System Prompt Injection in Slack Channel Descriptions

Published Feb 19, 2026 · Updated Feb 19, 2026 · Assigned by GitHub_M

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.

Affected products

VendorProductAffectedFixed
clawdbot clawdbot < 2026.2.3 —

Affected packages

EcosystemPackageAffectedFixedRecord
npm openclaw < 2026.2.3 2026.2.3 GHSA-782p-5fr5-7fj8

References