RCE in Clawdbot
CVE-2026-24764
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.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 3.7 (Low). Vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:L/A:N.
EPSS exploit prediction
EPSS 0.002, 15.7th percentile (last changed ); unchanged over 30 days. About EPSS.
Affected products
Weakness classification (CWE)
References
- https://github.com/openclaw/openclaw/security/advisories/GHSA-782p-5fr5-7fj8 (Exploit, Patch, Vendor Advisory)
- https://github.com/openclaw/openclaw/commit/35eb40a7000b59085e9c638a80fd03917c7a095e (Patch)
- https://github.com/openclaw/openclaw/releases/tag/v2026.2.3 (Product, Release Notes)