CVE-2025-11915VulnerabilityPublished 22 Oct 2025Updated 23 Oct 2025

CVE-2025-11915: Google Cloud Vertex AI: Partner Models for MaaS · HTTP Request/Response Smuggling

Affects Google Cloud Vertex AI: Partner Models for MaaSSource CVE Database V5

Not known to be exploited · CVSS 6.9 Medium.

Data as of 26 Oct 2026, 06:26 UTC

CVSS 4.0 base score

6.9Medium

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

EPSS: 0.3% chance of exploitation in 30 days – higher than 24% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:N/VA:L/SC:L/SI:N/SA:L/U:Clear

Base metrics

Attack Vector: Network
Attack Complexity: Low
Attack Requirements: None
Privileges Required: None
User Interaction: None
Vulnerable system confidentiality: Low
Vulnerable system integrity: None
Vulnerable system availability: Low
Subsequent system confidentiality: Low
Subsequent system integrity: None
Subsequent system availability: Low

Supplemental metrics

Provider Urgency: Clear

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

Attack Vector: Network: The vulnerable system is bound to the network stack and the set of possible attackers extends beyond the other options listed below, 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: The attacker must take no measurable action to exploit the vulnerability. The attack requires no target-specific circumvention to exploit the vulnerability. An attacker can expect repeatable success against the vulnerable system.
Attack Requirements: None: The successful attack does not depend on the deployment and execution conditions of the vulnerable system. The attacker can expect to be able to reach the vulnerability and execute the exploit under all or most instances of the vulnerability.
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files of the vulnerable system to carry out an attack.
User Interaction: None: The vulnerable system can be exploited without interaction from any human user, other than the attacker.
Vulnerable system confidentiality: Low: There is some loss of confidentiality. Access to some restricted information is obtained, but the attacker does not have control over what information is obtained, or the amount or kind of loss is limited. The information disclosure does not cause a direct, serious loss to the Vulnerable System.
Vulnerable system integrity: None: There is no loss of integrity within the Vulnerable System.
Vulnerable system 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 Vulnerable System 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 Vulnerable System.
Subsequent system confidentiality: Low: There is some loss of confidentiality. Access to some restricted information is obtained, but the attacker does not have control over what information is obtained, or the amount or kind of loss is limited. The information disclosure does not cause a direct, serious loss to the Subsequent System.
Subsequent system integrity: None: There is no loss of integrity within the Subsequent System or all integrity impact is constrained to the Vulnerable System.
Subsequent system 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 Subsequent System 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 Subsequent System.
Provider Urgency: Clear: Provider has assessed the impact of this vulnerability as having no urgency (Informational).

Definitions: FIRST CVSS v4.0 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 22 Oct 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
Google Cloud Vertex AI: Partner Models for MaaS	Affected =0	Fixed in–

AI-suggested

1. Verify that all Google Cloud Vertex AI Partner Models for MaaS services are running the latest patched versions, ensuring the fixes deployed by Google are active. 2. Review and update any custom HTTP proxy configurations or third-party proxies in front of AI model endpoints to ensure they correctly handle HTTP request parsing and do not introduce desynchronization. 3. Implement strict HTTP request validation and normalization at the proxy level to detect and block malformed or suspicious requests indicative of smuggling attempts. 4. Monitor HTTP traffic logs for anomalies such as unexpected request sequences, unusual header patterns, or inconsistent content lengths that may signal exploitation attempts. 5. Employ Web Application Firewalls (WAFs) with updated rulesets capable of detecting HTTP request smuggling techniques. 6. Conduct regular security assessments and penetration testing focusing on HTTP proxy and backend interactions within AI service architectures. 7. Educate DevOps and security teams about HTTP request smuggling risks and mitigation best practices specific to cloud AI services. 8. Coordinate with Google Cloud support to confirm that all relevant patches and mitigations are applied and to receive updates on any emerging threats related to this vulnerability.

Description

Connection desynchronization between an HTTP proxy and the model backend. The fixes were rolled out for all proxies in front of impacted models by 2025-09-28. Users do not need to take any action.

Impact

For European organizations leveraging Google Cloud Vertex AI Partner Models, this vulnerability could lead to unauthorized manipulation of HTTP traffic between proxies and backend AI models. Potential impacts include partial leakage of sensitive data processed by AI models, injection of malicious requests causing service disruption, and possible bypass of security controls relying on HTTP traffic inspection. Given the AI models may process sensitive or proprietary data, confidentiality impacts are significant. Availability impacts could manifest as degraded or interrupted AI service functionality, affecting business operations reliant on these models. The vulnerability's remote exploitability without authentication increases risk, especially for organizations with public-facing AI services or integrated APIs. However, since Google has already deployed fixes, the immediate risk is mitigated if organizations use up-to-date cloud services. Organizations that have custom proxy configurations or delay updates may remain vulnerable. The medium severity suggests that while the threat is serious, it is not critical, but still warrants attention to prevent potential data breaches or service interruptions.

CWE-444Inconsistent Interpretation of HTTP Requests ('HTTP Request/Response Smuggling') (opens in a new tab)
Base weaknessOWASP Top 10 A06:2025: Insecure Design (opens in a new tab)
The product acts as an intermediary HTTP agent (such as a proxy or firewall) in the data flow between two entities such as a client and server, but it does not interpret malformed HTTP requests or responses in ways that are consistent with how the messages will be processed by those entities that are at the ultimate destination.
Implementation
Use a web server that employs a strict HTTP parsing procedure, such as Apache.
Implementation
Use only SSL communication.
Implementation
Terminate the client session after each request.
OWASP Cheat Sheets
REST Assessment (opens in a new tab)
REST Security (opens in a new tab)
Cross-Site Request Forgery Prevention (opens in a new tab)
Secure Design Principles (opens in a new tab)
OWASP ASVS 4.0.3
V13.2.5 (opens in a new tab)
Attack patterns
HTTP Response Smuggling (opens in a new tab)
HTTP Request Smuggling (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

cloud.google.com/vertex-ai/generative-ai/docs/security-bulletins (opens in a new tab)

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 29 Oct 2025, 10:17 UTC

WeaknessesCWE-444

Technical details

References

Community reviews

Related threats