CVE-2026-100654

Description

References

• vllm-project/vllm security advisory · Mitigation
• vulncheck.com/advisories/vllm-before-0.29.0-denial-of-service-via-out-of-range-stop-token-ids · Third Party Advisory

More vulnerabilities in vllm

• CVE-2026-115918MEDIUM 6.5vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authentica…
• CVE-2026-115917MEDIUM 4.7vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMi…
• CVE-2026-115916MEDIUM 6.5vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-…
• CVE-2026-115915CRITICAL 9.8vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attacker-controlled image bytes to P…
• CVE-2026-115914MEDIUM 6.5vLLM is an inference and serving engine for large language models. From 0.11.1 until 0.32.0, the DeepSeek-OCR, DeepSeek-OCR-2, and Unlimited…