CVE-2025-33203VulnerabilityPublished 25 Nov 2025

CVE-2025-33203: NVIDIA NeMo Agent ToolKit · Server-Side Request Forgery (SSRF)

Affects NVIDIA NeMo Agent ToolKitSource CVE Database V5

Not known to be exploited · CVSS 7.6 High : upgrade to 1.3.0 soon.

Data as of 26 Oct 2026, 06:26 UTC

CVSS 3.1 base score

7.6High

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

EPSS: 0.2% chance of exploitation in 30 days – higher than 21% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 1.3.0

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

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

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: 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: 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: Low: Modification of data is possible, but the attacker does not have control over the consequence of a modification, or the amount of modification is limited. The data modification does not have a direct, serious impact on the impacted component.
Availability: Low: Performance is reduced or there are interruptions in resource availability. Even if repeated exploitation of the vulnerability is possible, the attacker does not have the ability to completely deny service to legitimate users. The resources in the impacted component are either partially available all of the time, or fully available only some of the time, but overall there is no direct, serious consequence to the impacted component.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 25 Nov 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

Upgrade nvidia/nemo-agent-toolkit to 1.3.0.

Affected software

Product	Affected	Fixed in
npmnvidia/nemo-agent-toolkit`pkg:npm/nvidia/nemo-agent-toolkit`Other threats	Affected <1.3.0	Fixed in 1.3.0

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

European organizations should immediately assess their use of NVIDIA NeMo Agent ToolKit and prioritize upgrading to version 1.3.0 or later once available. If you cannot patch yet, implement strict input validation and sanitization on all chat API endpoints to prevent malicious request payloads. Network segmentation should be enforced to limit the server's ability to reach sensitive internal resources or metadata services. Employ outbound request filtering and monitoring to detect and block anomalous or unauthorized server-initiated requests. Additionally, apply the principle of least privilege to the service accounts running the NeMo Agent ToolKit to minimize potential damage. Regularly review logs for unusual activity related to the chat API and consider deploying Web Application Firewalls (WAFs) with custom rules to detect SSRF patterns. Finally, maintain awareness of NVIDIA security advisories for timely patch deployment.

Description

NVIDIA NeMo Agent Toolkit UI for Web contains a vulnerability in the chat API endpoint where an attacker may cause a Server-Side Request Forgery. A successful exploit of this vulnerability may lead to information disclosure and denial of service.

Impact

For European organizations, the impact of this SSRF vulnerability can be significant, especially for those using NVIDIA NeMo Agent ToolKit in AI development, customer service automation, or internal tooling. Confidentiality risks include unauthorized access to internal network resources, databases, or cloud metadata services, potentially exposing sensitive personal data protected under GDPR. Integrity risks, while lower, could involve manipulation of internal API responses or partial disruption of services. Availability could be affected if attackers leverage the vulnerability to cause denial of service, impacting business continuity. Given the increasing adoption of AI tools in sectors such as finance, healthcare, and manufacturing across Europe, exploitation could lead to regulatory penalties, reputational damage, and operational disruptions. The vulnerability's remote exploitability without user interaction increases the risk of automated attacks or inclusion in broader attack campaigns targeting AI infrastructure.

CWE-918Server-Side Request Forgery (SSRF) (opens in a new tab)
Base weaknessCWE Top 25 (2025): #22OWASP Top 10 A01:2025: Broken Access Control (opens in a new tab)
The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.
OWASP Cheat Sheets
Server Side Request Forgery Prevention (opens in a new tab)
Unvalidated Redirects and Forwards (opens in a new tab)
Cross Site Scripting Prevention (opens in a new tab)
DOM based XSS Prevention (opens in a new tab)
Authorization (opens in a new tab)
OWASP ASVS 4.0.3
V12.6.1 (opens in a new tab)
V5.2.6 (opens in a new tab)
Attack patterns
Server Side Request Forgery (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 2 Dec 2025, 18:43 UTC

WeaknessesCWE-918

Technical details

References

Community reviews

Related threats