Browse / Improper Output Handling / CVE-2026-4963
Hugging Face Smolagents has an Injection issue
- Class
- Improper Output Handling (filed by a model that read the advisory)
- Technique
- Code and command execution
- Also involves
- Tool and Agent Misuse
- Affected
- smolagents (PyPI)
- Gets past
- Sandbox or allowlist
- CVSS
- CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:L
- EPSS
- 0.6% chance of exploitation in 30 days
How it works, in short
The local Python executor that runs agent-generated code fails to block some constructs, so crafted code escapes its restrictions and runs commands. (Our summary, written by a model. The source text is below.)
Details
A weakness has been identified in huggingface smolagents 1.25.0.dev0. This affects the function evaluate_augassign/evaluate_call/evaluate_with of the file src/smolagents/local_python_executor.py of the component Incomplete Fix CVE-2025-9959. This manipulation causes code injection. It is possible to initiate the attack remotely. The exploit has been made available to the public and could be used for attacks. The vendor was contacted early about this disclosure but did not respond in any way.
References
- https://nvd.nist.gov/vuln/detail/CVE-2026-4963
- https://gist.github.com/YLChen-007/35b7d46e892266a0ed6dbe57802858be
- https://gist.github.com/YLChen-007/7146f45960f79bc1e2976fed526e0a9b
- https://github.com/huggingface/smolagents
- https://vuldb.com/?ctiid.353840
- https://vuldb.com/?id.353840
- https://vuldb.com/?submit.777623
- https://vuldb.com/?submit.777643
- https://vuldb.com/?submit.777644
Source: GitHub Advisory Database, used under CC BY 4.0.