Sign In
Advisories

vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense

Go back
Severity
medium
Date
Affecting

  • vllm >= 0, < 0.31.0

CWE
  • CWE-440 Expected Behavior Violation
CVSS
6.3
CVSS V4 Vector
CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N
Credit
glaziermag, jperezdealgaba, SunnyR
Description
vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense() that allows remote attackers to constrain other clients' outputs by leaving stale allowed_token_ids rows. Attackers can submit concurrent constrained generate requests, including via unauthenticated /invocations, so recycled batch slots apply their token allowlist to victims' unrestricted requests.

Ready to get Started?

Explore VulnCheck, a next-generation Cyber Threat Intelligence platform, which provides exploit and vulnerability intelligence to help you prioritize and remediate vulnerabilities that matter.
  • Vulnerability Prioritization
    Prioritize vulnerabilities that matter based on the threat landscape and defer vulnerabilities that don't.
  • Early Warning System
    Real-time alerting of changes in the vulnerability landscape so that you can take action before the attacks start.
Schedule a Demo