CVE-2026-24222: CWE-497 Exposure of Sensitive System Information to an Unauthorized Control Sphere in NVIDIA NemoClaw
NVIDIA NeMoClaw has a vulnerability in its sandbox environment initialization component that allows a remote attacker to cause improper access control. By sending prompt-injected content, the attacker can cause the agent to read and exfiltrate host environment variables that are not properly restricted during sandbox creation. This vulnerability can lead to the disclosure of sensitive system information. It affects all versions prior to v0.0.18. The vulnerability has a high severity with a CVSS score of 8.6. There is no confirmed patch or official remediation available at this time.
AI Analysis
Technical Summary
CVE-2026-24222 is a vulnerability in NVIDIA NeMoClaw's sandbox environment initialization component. The flaw allows a remote attacker to inject prompts that cause the agent to improperly access and disclose host environment variables during sandbox creation. This results in exposure of sensitive system information due to inadequate access control. The vulnerability affects all versions prior to v0.0.18 and has a CVSS 3.1 base score of 8.6, indicating high severity. No official patch or remediation level has been published by NVIDIA as of the data provided.
Potential Impact
Successful exploitation of this vulnerability can lead to unauthorized disclosure of sensitive system information by exfiltrating host environment variables. This could compromise confidentiality but does not affect integrity or availability. There are no known exploits in the wild currently.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is released, users should consider restricting network access to the vulnerable component and monitor for suspicious activity related to prompt injection. Avoid deploying affected versions in untrusted environments where remote attackers could interact with the sandbox initialization process.
CVE-2026-24222: CWE-497 Exposure of Sensitive System Information to an Unauthorized Control Sphere in NVIDIA NemoClaw
Description
NVIDIA NeMoClaw has a vulnerability in its sandbox environment initialization component that allows a remote attacker to cause improper access control. By sending prompt-injected content, the attacker can cause the agent to read and exfiltrate host environment variables that are not properly restricted during sandbox creation. This vulnerability can lead to the disclosure of sensitive system information. It affects all versions prior to v0.0.18. The vulnerability has a high severity with a CVSS score of 8.6. There is no confirmed patch or official remediation available at this time.
CVSS v3.1
Score 8.6high
Affected software
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-24222 is a vulnerability in NVIDIA NeMoClaw's sandbox environment initialization component. The flaw allows a remote attacker to inject prompts that cause the agent to improperly access and disclose host environment variables during sandbox creation. This results in exposure of sensitive system information due to inadequate access control. The vulnerability affects all versions prior to v0.0.18 and has a CVSS 3.1 base score of 8.6, indicating high severity. No official patch or remediation level has been published by NVIDIA as of the data provided.
Potential Impact
Successful exploitation of this vulnerability can lead to unauthorized disclosure of sensitive system information by exfiltrating host environment variables. This could compromise confidentiality but does not affect integrity or availability. There are no known exploits in the wild currently.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is released, users should consider restricting network access to the vulnerable component and monitor for suspicious activity related to prompt injection. Avoid deploying affected versions in untrusted environments where remote attackers could interact with the sandbox initialization process.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- nvidia
- Date Reserved
- 2026-01-21T19:09:36.964Z
- Cvss Version
- 3.1
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 69f1649fcbff5d861047eebc
Added to database: 4/29/2026, 1:53:35 AM
Last enriched: 5/6/2026, 2:13:11 AM
Last updated: 6/12/2026, 2:48:50 PM
Views: 65
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.