CVE-2026-61539

Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval in xinference/model/llm/toolparsers/llama3toolparser.py and xinference/model/llm/utils.py. Requests to...

GHSA-X2RJ-828P-HX9M Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing

Summary Xinference used Python's unsafe eval function when parsing Llama3 tool-call output generated by a large language model. Because the model output can be influenced by attacker-controlled prompts sent to the chat completion API, a remote attacker can craft prompts that cause the model to...

CVE-2026-61539 Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing

Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval in xinference/model/llm/toolparsers/llama3toolparser.py and xinference/model/llm/utils.py. Requests to...

EUVD-2026-64146

Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval in xinference/model/llm/toolparsers/llama3toolparser.py and xinference/model/llm/utils.py. Requests to...

PT-2026-80328

Summary Xinference used Python's unsafe eval function when parsing Llama3 tool-call output generated by a large language model. Because the model output can be influenced by attacker-controlled prompts sent to the chat completion API, a remote attacker can craft prompts that cause the model to...

PYSEC-2026-2014 vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder

Summary An unsafe deserialization vulnerability allows any authenticated user to execute arbitrary code on the server if they are able to get the model to pass the code as an argument to a tool call. Details vLLM's Qwen3 Coder tool parser contains a code execution path that uses Python's eval...

vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder

SummaryAn unsafe deserialization vulnerability allows any authenticated user to execute arbitrary code on the server if they are able to get the model to pass the code as an argument to a tool call. Details vLLM's Qwen3 Coder tool parser contains a code execution path that uses Python's eval...

GHSA-VFM7-4H43-GP6M Duplicate Advisory: vLLM Vulnerable to Regular Expression Denial of Service

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-j828-28rj-hfhp. This link is maintained to preserve external references. Original Description vLLM versions = 0.6.3 and 0.9.0 contain multiple regular expression denial of service ReDoS vulnerabilities. Several...

PT-2026-90009

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-j828-28rj-hfhp. This link is maintained to preserve external references. Original Description vLLM versions = 0.6.3 and 0.9.0 contain multiple regular expression denial of service ReDoS vulnerabilities. Several...

CVE-2025-71379: Inefficient Regular Expression Complexity

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...

The vulnerability of the pythonic_tool_parser.py script from the library for working with large language models (LLMs), vLLM, allows a perpetrator to trigger a service failure.

The vulnerability of the pythonictoolparser.py script, a library for working with large language models LLMs, is related to the use of a regular expression with inefficient computational complexity. Exploiting this vulnerability could allow a malicious actor to cause service failures...

Deserialization of Untrusted Data

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Deserialization of Untrusted Data via the convertparamvalue function in the Qwen3CoderToolParser class, which uses eval function to parse tool call...

vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder

Summary An unsafe deserialization vulnerability allows any authenticated user to execute arbitrary code on the server if they are able to get the model to pass the code as an argument to a tool call. Details vLLM's Qwen3 Coder tool parser contains a code execution path that uses Python's eval...

GHSA-79J6-G2M3-JGFW vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder

Summary An unsafe deserialization vulnerability allows any authenticated user to execute arbitrary code on the server if they are able to get the model to pass the code as an argument to a tool call. Details vLLM's Qwen3 Coder tool parser contains a code execution path that uses Python's eval...

PYSEC-2025-50

vLLM, an inference and serving engine for large language models LLMs, has a Regular Expression Denial of Service ReDoS vulnerability in the file vllm/entrypoints/openai/toolparsers/pythonictoolparser.py of versions 0.6.4 up to but excluding 0.9.0. The root cause is the use of a highly complex and...

Regular Expression Denial of Service (ReDoS)

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Regular Expression Denial of Service ReDoS through the pythonictoolparser.py. An attacker can cause severe performance degradation or make the servi...