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

Low 3.7 Published Updated

Attackers can achieve remote code execution by injecting malicious prompts into Slack channel descriptions when the integration is enabled.

Exploited in the wild
Not known
Login needed
Any signed-in user
Attackable
Over the internet
Victim action needed
A user has to click or open something
Fix
Available

What is CVE-2026-24764?

CVE-2026-24764 is a low-severity code injection vulnerability in Openclaw Openclaw, published on 19 Feb 2026. Any signed-in user can exploit it over the network, and only if a user opens a file or follows a link.

Official 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.

Weakness: CWE-94, CWE-74

Which versions are affected by CVE-2026-24764?

2 open source packages ship an affected version, including openclaw. It affects 1 product.

PackageAffectedFixed in
openclaw npmAll versions2026.2.3
openclaw npmAll versions2026.2.3

Products include Openclaw Openclaw.

How do I fix CVE-2026-24764?

Upgrade openclaw to 2026.2.3 or later.

Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.

Is CVE-2026-24764 being exploited?

There is no known exploitation of CVE-2026-24764 in the wild and no public exploit code.

All Openclaw Openclaw vulnerabilities

Sources

Also known as GHSA-782p-5fr5-7fj8.

Is CVE-2026-24764 in your software?

Upload an SBOM and sbomify checks it against every vulnerability here, every day.

Check your SBOMs for free