HighVulnerabilityLLM-specific
CVE-2026-130686: vLLM resource exhaustion through many remote image URLs in one request
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-130686
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
Summary
vLLM versions from 0.6.0 before 0.33.0 lack a request-wide media budget. A remote inference client can send one compact request to /v1/messages or /v1/responses containing many remote image URLs, forcing every image to be downloaded and decoded before prompt-length admission, which exhausts memory, CPU, and connections.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Topics
Related items
- HighCVE-2026-130685: vLLM denial of service through out-of-range prompt token ids in /v1/completionsSimilar attack · NVD/CVE Database
- MediumCVE-2026-126399: vLLM resource exhaustion via video frame limit bypass in chat completionsSimilar attack · NVD/CVE Database
- MediumCVE-2026-126398: vLLM reachable assertion crash in GPUModelRunner via embeddings-only requestsSimilar attack · NVD/CVE Database
- HighCVE-2026-126397: vLLM denial of service via unbounded max_patches in multimodal preprocessingSimilar attack · NVD/CVE Database
- MediumCVE-2026-126396: vLLM resource exhaustion in MiniMax M3 VL video processor via min_pixelsSimilar attack · NVD/CVE Database