LLMMedium
CVE-2026-24764: OpenClaw (formerly Clawdbot) is a personal AI assistant users run on their own devices. In versions …
- Occurred
- Feb 19, 2026
- Published
- Feb 19, 2026
- Source
- NVD CVE
Summary
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.
Tags
- CVE
- CVE-2026-24764
- cvss:LOW
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: Prompt injection vulnerability in LLM system prompt via untrusted Slack metadata.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8