CVE-2026-61539Critical· 10.0▾ MidnightXinference 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/tool_parsers/llama3_tool_parser.…
▾ Midnight zone — Critical, or high with PoC / in-the-wild
impact 55 · likelihood 0.2 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Exploit-prediction probability, daily snapshots since Aug 22.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
0.7%
0.7% → 1.2%
Last analysed / modified upstream
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/tool_parsers/llama3_tool_parser.py and xinference/model/llm/utils.py. Requests to /v1/chat/completions with a tools field flow through xinference/api/restful_api.py, xinference/model/llm/transformers/core.py, handle_chat_result_non_streaming(), and _post_process_completion() before extract_tool_calls() or _eval_llama3_chat_arguments() evaluates the model-generated Python expression. An unauthenticated remote attacker can influence that output through a crafted prompt and execute commands in the Xinference server process context. This issue is fixed in version 2.7.0.
Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Affected packages:
xinference < 2.7.0Patched in:
xinference 2.7.0Connected by shared product, vendor, weakness, or advisory.
CVE-2026-76841High· 8.8Xinference loads models with Hugging Face remote code execution unconditionally enabled, and before version 2.12.0 exposes no setting to disable it
CVE-2024-46946Critical· 9.8LangChain Experimental Eval Injection vulnerability
CVE-2026-61433High· 7.8PraisonAI: API deploy code generator embeds unescaped YAML fields into Python source
CVE-2026-35002Critical· 9.8Agno versions prior to 2.3.24 contain an arbitrary code execution vulnerability in the model execution component that allows attackers to execute arbitrary Python code by manipulating the field_type parameter passed to eval()
CVE-2026-10561Critical· 9.9Langflow: PythonREPLComponent executes unsandboxed Python code, enabling authenticated RCE and privilege escalation
CVE-2026-105315Medium· 4.7A vulnerability has been found in django-haystack up to 3.3.0