Vulnerability 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 Score
LOW
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Openclaw | Openclaw | < 2026.2.3 |
Related Weaknesses (CWE)
References
- https://github.com/openclaw/openclaw/commit/35eb40a7000b59085e9c638a80fd03917c7aPatch
- https://github.com/openclaw/openclaw/releases/tag/v2026.2.3ProductRelease Notes
- https://github.com/openclaw/openclaw/security/advisories/GHSA-782p-5fr5-7fj8ExploitPatchVendor Advisory
FAQ
What is CVE-2026-24764?
CVE-2026-24764 is a vulnerability with a CVSS score of 3.7 (LOW). 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 ...
How severe is CVE-2026-24764?
CVE-2026-24764 has been rated LOW with a CVSS base score of 3.7/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-24764?
Check the references section above for vendor advisories and patch information. Affected products include: Openclaw Openclaw.