Authenticated service interruption via attacker-controlled tokenization flag
Published Nov 21, 2025 · Updated Nov 24, 2025
Denial of service in vLLM 0.5.5 through 0.11.0 allows remote authenticated users to block API processing via crafted requests. The chat and tokenize handlers unpack attacker-controlled chat_template_kwargs into apply_hf_chat_template, allowing tokenize=True to synchronously tokenize oversized input on the API server event loop. An API credential and access to either affected endpoint are required; successful requests delay all other API traffic until tokenization finishes.
Summary
What happened
Denial of service in vLLM 0.5.5 through 0.11.0 allows remote authenticated users to block API processing via crafted requests. The chat and tokenize handlers unpack attacker-controlled chat_template_kwargs into apply_hf_chat_template, allowing tokenize=True to synchronously tokenize oversized input on the API server event loop. An API credential and access to either affected endpoint are required; successful requests delay all other API traffic until tokenization finishes.
The record
- CVE
- CVE-2025-62426
- Published
- Nov 21, 2025
- Updated
- Nov 24, 2025
- Vendor
- vLLM Project
- Product
- vLLM
- Classifications
- CWE-770, T1499
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Nov 21, 2025CVE publishedPublication date reported by the CVE source.
- Nov 24, 2025Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=>= 0.5.5, < 0.11.1
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo