CVE-2026-24764 | OpenClaw has Remote Code Execution via System Prompt Injection in Slack Channel Descriptions

Exp

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: 2026-02-19 Last update: 2026-02-19 Assigner: [email protected] Source: [email protected]

Conclusion & alert: CVE-2026-24764 is rated Exploit Available (50/100): CVSS Low severity, with low exploitation likelihood (EPSS 0.03%). Core evidence: 1 public exploit reference(s) are indexed (Exploit-DB). Mandatory action: Public exploits are available—assess exposure, apply mitigations, and prioritize patching.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Public exploit references (Exploit-DB) for CVE-2026-24764

EDB-ID Source Kind Published Link
nvd_ref exploit_tag Exploit-DB ↗

Exploit prediction scoring system (EPSS) score for CVE-2026-24764

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-02-19 0.03%

Full EPSS history (1 record total)

Common vulnerability scoring system (CVSS) metrics for CVE-2026-24764

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
3.7 3.1 LOW
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:L/A:N Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:H)
Even with access, the exploit needs extra luck, timing, or a fussy environment to actually work.
Privileges required (PR:L)
A normal user session is enough; they don’t have to be admin.
User interaction (UI:R)
A real person has to do something—click, install, enable—otherwise it doesn’t land.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:L)
Some sensitive info could get out, but not a total data dump.
Integrity (I:L)
Attackers could change some data, but it’s limited—not everything goes.
Availability (A:N)
Service keeps running; no real outage angle.
1.2 2.5 [email protected]

Weakness enumeration for CVE-2026-24764

GitHub Security Advisory for CVE-2026-24764

GHSA-782p-5fr5-7fj8 · Severity: low · Ecosystem: npm — OpenClaw Affected by Remote Code Execution via System Prompt Injection in Slack Channel Descriptions

Affected software / configurations for CVE-2026-24764

Vendor Product Version Raw CPE
openclaw openclaw < 2026.2.3 cpe:2.3:a:openclaw:openclaw:*:*:*:*:*:node.js:*:*

References for CVE-2026-24764

cvelogic Threat Intelligence