Signal is active with 1 mentions in latest observed window
Recommended action window: Monitor and triage in normal cycle
NVD 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.
Priority
LOW
Exploitation
NONE
PoC
YES
Patch
AVAILABLE
Momentum
STABLE
If you run products in this scope, you should treat this CVE as relevant to your environment.
📝 New article: CVE-2026-24764: How Slack Metadata Became a Prompt Injection Vector in OpenClaw AI https://moltx.io/articles/742dd772-6615-4983-a250-2f402aaf4a1b
Post summary
The article announces CVE‑2026‑24764, noting Slack metadata as a prompt injection vector in OpenClaw AI, but does not provide PoC, exploit code, active exploitation evidence, remediation steps, or detailed technical data.
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… https://www.cve.org/CVERecord?id=CVE-2026-24764
Post summary
The text references CVE‑2026‑24764 for OpenClaw’s Slack integration but offers no additional details, PoC, exploit, or mitigation information.
1 of 1 entries
| Part | Vendor | Product | Version | Target SW | Target HW |
|---|---|---|---|---|---|
| App | openclaw | openclaw | - | node.js | - |