GHSA-ph72-cqr5-qpp7: vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features
- Identifiers
- CVE-2026-105754GHSA-ph72-cqr5-qpp7
- Published
- Record updated
- Affected
- vllm < 0.30.0
- Fixed in
- 0.30.0
- released September 22, 2026, 13 days before disclosure
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.3%
Summary
vLLM versions up to and including 0.25.1 are affected through the disaggregated scale-out transport. The POST /inference/v1/generate route decodes a caller-supplied features object (kwargs_data, mm_hashes, mm_placeholders) and passes it to the engine as if it came from the trusted render step, without validating it against the active model's renderer output. Any authenticated caller can forge one field to crash the shared EngineCore process, poison or disclose cross-request encoder-cache state, or drop placeholder masks during replay.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Affected packages in the Exposure Registry
Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.
- vllmPyPILLM dependency since 2023-08-25 · 15 tracked dependents
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
- MediumWhen Shuffling Fails: Token Recovery from Obfuscated KV CachesSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)