CVE-2026-24764
OpenClaw has Remote Code Execution via System Prompt Injection in Slack Channel Descriptions
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.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- High
- Privileges needed
- Low
- User interaction
- Required
What an attacker can affect
- Confidentiality
- Low
- Integrity
- Low
- Availability
- None
Exploit likelihood
What each source reports
CVE List Score used
3.7
OpenClaw has Remote Code Execution via System Prompt Injection in Slack Channel Descriptions
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.
- Record
CVE-2026-24764- CVSS 3.1
- 3.7 Low
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:L/A:N - Weakness
- CWE-74, CWE-94
- Updated
- 2026-11-02
EUVDEUVD-2026-8120
3.7
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.
- Record
EUVD-2026-8120- CVSS 3.1
- 3.7 Low
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:L/A:N - Updated
- 2026-11-02
GitHub AdvisoriesGHSA-782p-5fr5-7fj8
3.7
OpenClaw Affected by Remote Code Execution via System Prompt Injection in Slack Channel Descriptions
Summary
When the Slack integration is enabled, Slack channel metadata (topic/description) could be incorporated into the model's system prompt.
Impact
Prompt injection is a documented risk for LLM-driven systems. This issue increased the injection surface by allowing untrusted Slack channel metadata to be treated as higher-trust system input.
This is relevant only for deployments that enable Slack. In deployments where tool execution is enabled, a successful injection could lead to unintended tool invocations and/or unintended data exposure.
Affected Packages / Versions
- npm:
openclaw< 2026.2.3
Patched Versions
- npm:
openclaw>= 2026.2.3
Mitigation
- If you do not use Slack: no action required.
- If you use Slack: upgrade to a patched version.
Fix Commit(s)
- 35eb40a7000b59085e9c638a80fd03917c7a095e
Thanks @KonstantinMirin for reporting.
- Record
GHSA-782p-5fr5-7fj8- CVSS 3.1
- 3.7 Low
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:L/A:N - Weakness
- CWE-74, CWE-94
- Updated
- 2026-11-02
NVD
3.7
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.
- Record
CVE-2026-24764- CVSS 3.1
- 3.7 Low
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:L/A:N - Weakness
- CWE-74, CWE-94
- Updated
- 2026-11-02
OSV
3.7
OpenClaw has Remote Code Execution via System Prompt Injection in Slack Channel Descriptions
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.
- Record
CVE-2026-24764- CVSS 3.1
- 3.7 Low
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:L/A:N - Weakness
- CWE-74, CWE-94
- Updated
- 2026-11-02
OSVGHSA-782p-5fr5-7fj8
3.7
OpenClaw Affected by Remote Code Execution via System Prompt Injection in Slack Channel Descriptions
Summary
When the Slack integration is enabled, Slack channel metadata (topic/description) could be incorporated into the model's system prompt.
Impact
Prompt injection is a documented risk for LLM-driven systems. This issue increased the injection surface by allowing untrusted Slack channel metadata to be treated as higher-trust system input.
This is relevant only for deployments that enable Slack. In deployments where tool execution is enabled, a successful injection could lead to unintended tool invocations and/or unintended data exposure.
Affected Packages / Versions
- npm:
openclaw< 2026.2.3
Patched Versions
- npm:
openclaw>= 2026.2.3
Mitigation
- If you do not use Slack: no action required.
- If you use Slack: upgrade to a patched version.
Fix Commit(s)
- 35eb40a7000b59085e9c638a80fd03917c7a095e
Thanks @KonstantinMirin for reporting.
- Record
GHSA-782p-5fr5-7fj8- CVSS 3.1
- 3.7 Low
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:L/A:N - Weakness
- CWE-74, CWE-94
- Updated
- 2026-11-02
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
openclawnpm |
before 2026.2.3 | 2026.2.3 |
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2026-24764 is a low vulnerability (CVSS 3.7) in Clawdbot, published February 17, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.24%, the 15th percentile. Fixed in openclaw 2026.2.3.
References
github.com/openclaw/openclaw/security/advisories/GHSA-782p-5fr5-7fj8
github.com/openclaw/openclaw/commit/35eb40a7000b59085e9c638a80fd03917c7a095e
github.com/openclaw/openclaw/releases/tag/v2026.2.3
nvd.nist.gov/vuln/detail/CVE-2026-24764
github.com/advisories/GHSA-782p-5fr5-7fj8
github.com/CVEProject/cvelistV5/tree/main/cves/2026/24xxx/CVE-2026-24764.json
github.com/openclaw/openclaw