VulnerabilityPublished 17 Jul 2025Updated 26 Feb 2026

CVE-2025-23266: NVIDIA Container Toolkit · Untrusted Search Path

Affects NVIDIA Container ToolkitSource CVE Database V5

Not known to be exploited · CVSS 9.0 Critical : upgrade to 25.3.0 or 1.17.5 as a priority.

Data as of 26 Oct 2026, 14:05 UTC

CVSS 3.1 base score

9.0Critical

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 3.3% chance of exploitation in 30 days – higher than 88% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 25.3.0, 1.17.5

CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

Attack Vector: Adjacent
Attack Complexity: Low
Privileges Required: Low
User Interaction: None
Scope: Changed
Confidentiality: High
Integrity: High
Availability: High

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Adjacent: The vulnerable component is bound to the network stack, but the attack is limited at the protocol level to a logically adjacent topology. This can mean an attack must be launched from the same shared physical (e.g., Bluetooth or IEEE 802.11) or logical (e.g., local IP subnet) network, or from within a secure or otherwise limited administrative domain (e.g., MPLS, secure VPN to an administrative network zone).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: Low: The attacker is authorized with (i.e., requires) privileges that provide basic user capabilities that could normally affect only settings and files owned by a user. Alternatively, an attacker with Low privileges may have the ability to cause an impact only to non-sensitive resources.
User Interaction: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Changed: An exploited vulnerability can affect resources beyond the security scope managed by the security authority of the vulnerable component. In this case, the vulnerable component and the impacted component are different and managed by different security authorities.
Confidentiality: High: There is total loss of confidentiality, resulting in all resources within the impacted component being divulged to the attacker. Alternatively, access to only some restricted information is obtained, but the disclosed information presents a direct, serious impact.
Integrity: High: There is a total loss of integrity, or a complete loss of protection. For example, the attacker is able to modify any/all files protected by the impacted component. Alternatively, only some files can be modified, but malicious modification would present a direct, serious consequence to the impacted component.
Availability: High: There is total loss of availability, resulting in the attacker being able to fully deny access to resources in the impacted component; this loss is either sustained (while the attacker continues to deliver the attack) or persistent (the condition persists even after the attack has completed). Alternatively, the attacker has the ability to deny some availability, but the loss of availability presents a direct, serious consequence to the impacted component (e.g., the attacker cannot disrupt existing connections, but can prevent new connections; the attacker can repeatedly exploit a vulnerability that, in each instance of a successful attack, leaks a only small amount of memory, but after repeated exploitation causes a service to become completely unavailable).

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 17 Jul 2025
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade NVIDIA Container Toolkit to 25.3.0 or 1.17.5.

Affected software

Product	Affected	Fixed in
NVIDIA Container Toolkit	Affected <1.17.5 <25.3.0	Fixed in 1.17.5 25.3.0

AI-suggested

If you cannot patch yet, implement the following specific measures: 1) Restrict write permissions on directories and environment variables involved in container initialization to trusted users only, preventing attackers from placing malicious executables or libraries in search paths. 2) Use container runtime security features such as seccomp, AppArmor, or SELinux to limit the capabilities of container processes and reduce the impact of potential code execution. 3) Employ strict image signing and verification to ensure only trusted container images are deployed. 4) Monitor container initialization logs and system audit logs for unusual activity indicative of exploitation attempts. 5) Isolate GPU-enabled containers in dedicated namespaces or hosts to limit lateral movement if compromise occurs. 6) Regularly review and harden container orchestration configurations to minimize exposure. 7) Educate DevOps and security teams about the risks of untrusted search paths and enforce secure coding and deployment practices. These targeted actions go beyond generic advice and address the root cause of the vulnerability.

Description

NVIDIA Container Toolkit for all platforms contains a vulnerability in some hooks used to initialize the container, where an attacker could execute arbitrary code with elevated permissions. A successful exploit of this vulnerability might lead to escalation of privileges, data tampering, information disclosure, and denial of service.

Impact

The potential impact of CVE-2025-23266 is severe for organizations using NVIDIA Container Toolkit and GPU Operator in containerized environments. Successful exploitation can lead to privilege escalation, allowing attackers to gain elevated permissions beyond their initial access level. This can result in unauthorized data tampering, leakage of sensitive information, and disruption of critical services through denial of service attacks. Organizations relying on GPU-accelerated workloads for AI, machine learning, scientific computing, and cloud services are particularly at risk, as compromised containers could lead to broader infrastructure compromise. The vulnerability undermines the integrity and confidentiality of containerized applications and the host systems. Given the critical nature and ease of exploitation, attackers could leverage this flaw to move laterally within networks or establish persistent footholds. The absence of known exploits in the wild currently provides a window for proactive mitigation, but the risk of future exploitation remains high.

Summary

CVE-2025-23266 is an untrusted search path vulnerability (CWE-426) found in the NVIDIA Container Toolkit and NVIDIA GPU Operator. This vulnerability arises from insecure handling of hooks during container initialization, where the software searches for executables or libraries in directories that can be influenced by an attacker. If an attacker can place a malicious executable or library in a location that is searched before the legitimate one, they can cause the container initialization process to execute arbitrary code with elevated privileges. This flaw affects all versions of the NVIDIA Container Toolkit up to and including 1.17.7, with CDI mode affected in versions prior to 1.17.5, and NVIDIA GPU Operator up to 25.3.0 (CDI mode). The vulnerability allows attackers with low privileges (local or network) to escalate their privileges without requiring user interaction, potentially leading to full system compromise. The impact includes unauthorized data access, modification, and disruption of services. The vulnerability is critical, with a CVSS v3.1 score of 9.0, reflecting its ease of exploitation and severe consequences. Although no public exploits are currently known, the widespread use of NVIDIA GPUs in containerized environments for AI, machine learning, and HPC workloads makes this a significant risk. The vulnerability highlights the importance of secure path handling in container runtimes and GPU operator software.

CWE-426Untrusted Search Path (opens in a new tab)
Base weaknessLikelihood of exploit: HighOWASP Top 10 A08:2025: Software or Data Integrity Failures (opens in a new tab)
The product searches for critical resources using an externally-supplied search path that can point to resources that are not under the product's direct control.
Architecture and Design · Implementation · Attack Surface Reduction
Hard-code the search path to a set of known-safe values (such as system directories), or only allow them to be specified by the administrator in a configuration file. Do not allow these settings to be modified by an external party. Be careful to avoid related weaknesses such as CWE-426 and CWE-428.
Implementation
When invoking other programs, specify those programs using fully-qualified pathnames. While this is an effective approach, code that uses fully-qualified pathnames might not be portable to other systems that do not use the same pathnames.
Implementation
Remove or restrict all environment settings before invoking other programs. This includes the PATH environment variable, LD_LIBRARY_PATH, and other settings that identify the location of code libraries, and any application-specific search paths.
OWASP Cheat Sheets
Software Supply Chain Security (opens in a new tab)
Infrastructure as Code (opens in a new tab)
Attack patterns
Leveraging/Manipulating Configuration File Search Paths (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 27 Feb 2026, 00:58 UTC

WeaknessesCWE-426

Technical details

References

Community reviews

Related threats