inference: Improper Neutralization of Directives in Dynamically Evaluated Code
CVE-2026-61539 is a critical-severity improper neutralization of directives in dynamically evaluated code vulnerability in inference from Xorbitsai, with a CVSS 3.1 base score of 10.0 out of 10. It can be exploited remotely over the network by an unauthenticated attacker, without any action from a user. Affected inference versions: < 2.7.0. The record does not name a fixed version, so check the vendor advisory. There is no confirmed exploitation so far. EPSS estimates a 1.23% chance of exploitation within 30 days, higher than 69% of scored CVEs.
Critical severity: a successful attack would have severe impact.
What to do
- Check which version of inference you run against the affected versions below, and install the vendor's latest release.
- Read the advisory on github.com for workarounds and exact fixed builds.
- Until you can update, restrict network access to the affected service so it is not reachable from untrusted networks.
Affected products and versions
Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.
How the severity score breaks down
- Attack vector
- NetworkCan be exploited remotely over a network, including the internet.
- Attack complexity
- LowNo special conditions are needed; the attack works reliably.
- Privileges required
- NoneNo account or login is needed.
- User interaction
- NoneNo action by a victim is required.
- Scope
- ChangedThe attack can reach beyond the vulnerable component into other systems.
- Confidentiality
- HighAll data handled by the component can be read.
- Integrity
- HighData or code can be modified at will.
- Availability
- HighThe component can be taken down completely.
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H. Scored by CNA (github.com).
Official description
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.
Source: the CVE record as published by its numbering authority, via NVD and CVE.org.
The underlying weakness: Improper Neutralization of Directives in Dynamically Evaluated Code
The product receives input from an upstream component, but it does not neutralize or incorrectly neutralizes code syntax before using the input in a dynamic evaluation call (e.g. eval).
How developers prevent this class of flaw
- If possible, refactor your code so that it does not need to use eval() at all.
- For Python programs, it is frequently encouraged to use the ast.literal_eval() function instead of eval, since it is intentionally designed to avoid executing code. However, an adversary could still cause excessive memory or stack consumption via deeply nested structures, so the python documentation discourages use of ast.literal_eval() on untrusted data.
More Improper Neutralization of Directives in Dynamically Evaluated Code vulnerabilities (CWE-95)
Timeline
- CVE record published.
- CISA published its SSVC assessment (exploitation: none, automatable: yes, technical impact: total).
- Record last changed materially (score, affected products, status or references).
References
Patches and release notes
Other vulnerabilities in inference
- 7.5 High severity
- 8.8 High severity
Recent Improper Neutralization of Directives in Dynamically Evaluated Code vulnerabilities
- 9.9 Critical severity
- 7.8 High severity
- 7.8 High severity
- 7.8 High severity
- 9.8 Critical severity
- 9.9 Critical severity
Spotted an error? Tell us.