GHSA-vfm7-4h43-gp6mMedium· 4.3▾ SunlitDuplicate Advisory: vLLM Vulnerable to Regular Expression Denial of Service
▾ Sunlit zone — Low / medium · no exploitation signal
impact 23.7 · likelihood 0 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via GHSA
Last analysed / modified upstream
This advisory has been withdrawn because it is a duplicate of GHSA-j828-28rj-hfhp. This link is maintained to preserve external references.
vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabilities. Several regex patterns — in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint — are susceptible to catastrophic backtracking. An attacker submitting crafted input with nested or repeated structures can trigger severe CPU consumption and performance degradation, resulting in denial of service.
vllm >= 0.6.3, < 0.9.0Upgrade to a patched release:
vllm 0.9.0Connected by shared product, vendor, weakness, or advisory.
CVE-2025-71379Medium· 4.3vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabilities
CVE-2026-73556Medium· 5.3vLLM is an inference and serving engine for large language models
GHSA-8qpc-6rxx-4pxfHigh· 7.5Duplicate Advisory: vllm p2p never connected zmq_exhaustion
GHSA-f623-hjm8-5wg5Critical· 8.1Duplicate Advisory: vLLM: Request-controlled mm_processor_kwargs.code_revision allows remote code execution
CVE-2026-115911Medium· 6.5vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool
CVE-2026-115912High· 7.5vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled