CVE-2026-24222: CWE-497 Exposure of Sensitive System Information to an Unauthorized Control Sphere in NVIDIA NemoClaw
NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending prompt-injected content that causes the agent to read and exfiltrate host environment variables not properly restricted during sandbox creation. A successful exploit of this vulnerability might lead to information disclosure.
AI Analysis
Technical Summary
NVIDIA NemoClaw contains a vulnerability classified as CWE-497 (Exposure of Sensitive System Information to an Unauthorized Control Sphere) in its sandbox environment initialization component. A remote attacker can send specially crafted prompt-injected content that causes the agent to improperly access and disclose host environment variables that should be restricted during sandbox creation. This vulnerability affects all versions prior to v0.0.18 and has a CVSS 3.1 score of 8.6, indicating high severity. No official remediation or patch has been published by NVIDIA as of the data provided.
Potential Impact
Successful exploitation of this vulnerability allows a remote attacker to disclose sensitive host environment variables, potentially exposing confidential system information. The vulnerability does not impact integrity or availability but has a high confidentiality impact. No known active exploits have been reported.
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 exposure of affected NemoClaw instances and monitor for unusual activity related to sandbox initialization. Avoid using versions prior to v0.0.18 in sensitive environments if possible.
CVE-2026-24222: CWE-497 Exposure of Sensitive System Information to an Unauthorized Control Sphere in NVIDIA NemoClaw
Description
NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending prompt-injected content that causes the agent to read and exfiltrate host environment variables not properly restricted during sandbox creation. A successful exploit of this vulnerability might lead to information disclosure.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
NVIDIA NemoClaw contains a vulnerability classified as CWE-497 (Exposure of Sensitive System Information to an Unauthorized Control Sphere) in its sandbox environment initialization component. A remote attacker can send specially crafted prompt-injected content that causes the agent to improperly access and disclose host environment variables that should be restricted during sandbox creation. This vulnerability affects all versions prior to v0.0.18 and has a CVSS 3.1 score of 8.6, indicating high severity. No official remediation or patch has been published by NVIDIA as of the data provided.
Potential Impact
Successful exploitation of this vulnerability allows a remote attacker to disclose sensitive host environment variables, potentially exposing confidential system information. The vulnerability does not impact integrity or availability but has a high confidentiality impact. No known active exploits have been reported.
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 exposure of affected NemoClaw instances and monitor for unusual activity related to sandbox initialization. Avoid using versions prior to v0.0.18 in sensitive environments if possible.
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: 4/29/2026, 2:01:18 AM
Last updated: 4/29/2026, 6:27:09 AM
Views: 3
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.