vLLM from 0.28.0 before 0.30.0 contains a reachable assertion vulnerability in GPUModelRunner._init_xdrope_positions that allows remote attackers to crash the engine by submitting embeddings-only requests

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: High

The successful attack depends on the evasion or circumvention of security-enhancing techniques in place that would otherwise hinder the attack. These include: Evasion of exploit mitigation techniques, for example, circumvention of address space randomization (ASLR) or data execution prevention (DEP) must be performed for the attack to be successful; Obtaining target-specific secrets. The attacker must gather some target-specific secret before the attack can be successful. A secret is any piece of information that cannot be obtained through any amount of reconnaissance. To obtain the secret the attacker must perform additional attacks or break otherwise secure measures (e.g. knowledge of a secret key may be needed to break a crypto channel). This operation must be performed for each attacked target.

Attack Requirements: Present

The successful attack depends on the presence of specific deployment and execution conditions of the vulnerable system that enable the attack. These include: a race condition must be won to successfully exploit the vulnerability (the successfulness of the attack is conditioned on execution conditions that are not under full control of the attacker, or the attack may need to be launched multiple times against a single target before being successful); the attacker must inject themselves into the logical network path between the target and the resource requested by the victim (e.g. vulnerabilities requiring an on-path attacker).

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: None

There is no loss of confidentiality within the Vulnerable System.

Vulnerable system integrity: None

There is no loss of integrity within the Vulnerable System.

Vulnerable system availability: High

There is a total loss of availability, resulting in the attacker being able to fully deny access to resources in the Vulnerable System; 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 Vulnerable System (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).

Subsequent system confidentiality: None

There is no loss of confidentiality within the Subsequent System or all confidentiality impact is constrained to the Vulnerable 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: None

There is no impact to availability within the Subsequent System or all availability impact is constrained to the Vulnerable System.

Definitions: FIRST CVSS v4.0 specification.