CVE-2025-33208VulnerabilityPublished 3 Dec 2025

CVE-2025-33208: NVIDIA TAO · Uncontrolled Search Path Element

Affects NVIDIA TAOSource CVE Database V5

Not known to be exploited · CVSS 8.8 High.

Data as of 26 Oct 2026, 06:26 UTC

CVSS 3.1 base score

8.8High

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

EPSS: 0.4% chance of exploitation in 30 days – higher than 36% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.

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

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: Required
Scope: Unchanged
Confidentiality: High
Integrity: High
Availability: High

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

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files to carry out an attack.
User Interaction: Required: Successful exploitation of this vulnerability requires a user to take some action before the vulnerability can be exploited.
Scope: Unchanged: An exploited vulnerability can only affect resources managed by the same security authority. In this case, the vulnerable component and the impacted component are either the same, or both are managed by the same security authority.
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 3 Dec 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 2026-10-26.

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 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

Affected software

Product	Affected	Fixed in
NVIDIA TAO	Affected =6.25.7	Fixed in–

AI-suggested

European organizations should implement several targeted mitigation strategies beyond generic patching advice: 1) Immediately audit all NVIDIA TAO deployments to identify affected versions (6.25.7) and isolate them if possible. 2) Apply strict validation and sanitization of all resource paths used by TAO to prevent loading from untrusted locations. 3) Employ application whitelisting and code integrity checks to detect and block unauthorized resource loading. 4) Restrict user permissions to limit the ability to influence search paths or resource locations, minimizing privilege escalation risks. 5) Monitor logs and network traffic for unusual activity related to TAO, such as unexpected file loads or process executions. 6) Educate users about the risks of interacting with untrusted content that could trigger the vulnerability. 7) Engage with NVIDIA for timely patches or workarounds and plan for rapid deployment once available. 8) Consider network segmentation to isolate AI infrastructure from general user environments to reduce exposure. 9) Implement endpoint detection and response (EDR) tools capable of identifying exploitation attempts targeting TAO. These measures collectively reduce the attack surface and improve detection capabilities.

Description

CVE-2025-33208 is a high-severity vulnerability in NVIDIA TAO version 6.25.7 involving an uncontrolled search path element (CWE-427). This flaw allows an attacker to influence resource loading paths, potentially leading to privilege escalation, data tampering, denial of service, and information disclosure. Exploitation requires no privileges but does require user interaction. The vulnerability impacts confidentiality, integrity, and availability with a CVSS score of 8.8. No known exploits are currently reported in the wild. European organizations using NVIDIA TAO, especially in AI and machine learning deployments, should prioritize patching and implement strict path validation controls. Countries with significant AI research and technology sectors, such as Germany, France, and the UK, are most likely to be affected.

Impact

For European organizations, the impact of CVE-2025-33208 can be substantial, particularly in sectors relying heavily on AI and machine learning technologies where NVIDIA TAO is deployed. Successful exploitation could lead to unauthorized privilege escalation, allowing attackers to execute arbitrary code or commands with elevated rights, potentially compromising entire systems. Data tampering could undermine the integrity of AI models or datasets, leading to flawed outputs or decisions. Denial of service could disrupt critical AI workflows, impacting business continuity. Information disclosure risks could expose sensitive intellectual property or personal data, raising compliance concerns under GDPR. The vulnerability’s network accessibility and lack of required privileges increase the attack surface, making remote exploitation feasible if user interaction can be induced. This elevates the threat level for organizations with remote or hybrid work environments. The absence of known exploits currently provides a window for proactive defense, but also means attackers may develop exploits rapidly once details are public.

Summary

CVE-2025-33208 is a vulnerability classified under CWE-427 (Uncontrolled Search Path Element) affecting NVIDIA's TAO platform, specifically version 6.25.7. The vulnerability arises because the software loads resources from paths that can be influenced or controlled by an attacker, allowing them to inject malicious resources or binaries. This can lead to multiple adverse outcomes including escalation of privileges, where an attacker gains higher access rights than intended; data tampering, where integrity of data can be compromised; denial of service, by disrupting normal operations; and information disclosure, leaking sensitive data. The CVSS v3.1 score of 8.8 reflects a high severity due to the network attack vector (AV:N), low attack complexity (AC:L), no privileges required (PR:N), but requiring user interaction (UI:R). The scope is unchanged (S:U), but the impact on confidentiality, integrity, and availability is high (C:H/I:H/A:H). Although no exploits are currently known in the wild, the vulnerability’s nature makes it a significant risk, especially in environments where TAO is used for AI model training and deployment. The lack of available patches at the time of publication necessitates immediate mitigation steps to reduce exposure.

CWE-427Uncontrolled Search Path Element (opens in a new tab)
Base weaknessOWASP Top 10 A08:2025: Software or Data Integrity Failures (opens in a new tab)
The product uses a fixed or controlled search path to find resources, but one or more locations in that path can be under the control of unintended actors.
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 · Attack Surface Reduction
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 · Attack Surface Reduction
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)
Search Order Hijacking (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 10 Dec 2025, 18:36 UTC

WeaknessesCWE-427

Technical details

References

Community reviews

Related threats