Findings

CVE-2026-24222

NVIDIA NeMoClaw contains a vulnerability in the sandbox environment initialization component, where a remote attacker could cause improper access control by sending pr…

Published Apr 28, 2026 · updated Jun 17, 2026 · 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.

Code

The project this record applies to. Exploit listings stay in References.

No public source repository is identified for this product.

Timeline

Detection, updates, and resolution for this record.

  1. Apr 28, 2026 · NIST NVD

    Detected

    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.

  2. Jun 17, 2026 · NIST NVD

    Updated

    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.

Affected

  • cpe nvidia/nemoclawversion unspecified

Sources

  • CVE.orgVulnerability recordCVE-2026-24222

    Official CVE identifier

    cve.org
  • NIST NVDVulnerability recordCVE-2026-24222

    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 restri

    nvd.nist.gov

References

CVE-2026-24222 · ZeroDay Findings