CVE-2026-24764

What it is

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.

At a glance

Exploitability

Can be exploited over the network with a low-privilege account, but needs a user to act. Limited direct impact.

Exploit odds

0.2% chance of exploitation in the next 30 days (EPSS).

Fix

A patch, advisory or fixed version is referenced. Upgrade or apply it.

Timeline

1. 2026-02-19 07:17 UTC PublishedDisclosed publicly on CVE.org and NVD
2. 2026-06-17 10:23 UTC Last updatedMost recent change to the record

Why it ranks here

• Exploited in the wild: no, CISA does not list it.
• Exploit odds: 0.2% in the next 30 days (EPSS).
• Severity: 3.7 LOW (CVSS).
• Fix: a patch or advisory is linked.

Details

Published

2026-02-19 07:17 UTC

Last modified

2026-06-17 10:23 UTC

Exploit probability

0.2% · EPSS, next 30 days

Weakness

CWE-74

Record status

Analyzed

Affected

• Openclaw < 2026.2.3

Attack profile CVSS 3.1 · 3.7

Attack vector

Network

Complexity

High

Privileges needed

Low

User interaction

Required

Scope

Unchanged

Confidentiality

Low

Integrity

Low

Availability

None

Is it in your code?

Hand this to your coding agent. It searches your project for the affected products and checks versions. Nothing leaves your machine.

Read https://cve-list.com/agent/cve/CVE-2026-24764.md and follow it. Check whether this project is affected by CVE-2026-24764. Read only. Don't change anything and don't upload my code. Tell me yes, no or not sure, with the file as proof.

Copy as ticket · More options · Status badge