MediumVulnerabilityLLM-specific
CVE-2026-105759: vLLM Rust frontend memory exhaustion via unique HTTP method labels in metrics
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-105759
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.4%
Summary
vLLM, an inference and serving engine for large language models, is affected before version 0.30.0 by a flaw in the Rust frontend's track_http_metrics middleware. The middleware records the raw HTTP method token as a Prometheus label on requests reaching registered routes, so an unauthenticated attacker sending unique arbitrary method tokens to unguarded routes such as /tokenize can permanently create label sets. This increases process memory usage and enlarges the /metrics response until the service or monitoring path is exhausted.
Mitigation
Fixed in version 0.30.0.
Topics
Related items
- LowToken fraud is here and it’s BAD (YouTube)Similar attack · Simon Willison's Weblog
- HighCVE-2026-133161: Pydantic AI Harness ToolOutputLimits ANSI stripping slowed by quadratic regexSimilar attack · NVD/CVE Database
- HighCVE-2026-130686: vLLM resource exhaustion through many remote image URLs in one requestSimilar attack · NVD/CVE Database
- HighCVE-2026-130685: vLLM denial of service through out-of-range prompt token ids in /v1/completionsSimilar attack · NVD/CVE Database
- LowRented Oscillations: Multi-Tenant Data Center Workload Synchronization Attacks and MitigationSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)