CVE-2026-54769

CRITICALCVSS 10/10EPSS 0.91%

Last modified

CVE-2026-54769 is a critical-severity vulnerability rated 10/10 on the CVSS scale. Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to a critical Sandbox Escape leading to Remote Code Execution (RCE) in its `TableChatAgent` and `VectorStore` capabilities. EPSS estimates a 0.91% chance of exploitation in the next 30 days.

Description

Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to a critical Sandbox Escape leading to Remote Code Execution (RCE) in its `TableChatAgent` and `VectorStore` capabilities. When these agents evaluate LLM-generated tool messages with `full_eval=True`, they attempt to sandbox the execution by explicitly setting `locals` to an empty dictionary `{}` inside Python's `eval()` function. However, this relies on an incomplete understanding of Python's execution model. Because `__builtins__` is not explicitly scrubbed from the `globals` dictionary mapping, Python implicitly injects all built-ins during execution, granting full access to functions like `__import__('os').system()`. Since `TableChatAgent.pandas_eval()` executes external LLM outputs natively, this bypass permits any attacker providing prompt payload to achieve unauthenticated RCE on the host system. Version 0.65.2 patches the issue.

Metrics

CVSS 3.1
10/10

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

EPSS Probability
0.91%

55.8th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

Affected Software

Source: CNA advisory (CVE.org). NVD analysis pending.

VendorProductVersions
langroidlangroid< 0.65.2

References

Timeline

Published
Last Modified
Status
Deferred

Frequently Asked Questions

What is CVE-2026-54769?
Langroid is a framework for building large-language-model-powered applications. Versions prior to 0.65.2 are vulnerable to a critical Sandbox Escape leading to Remote Code Execution (RCE) in its `TableChatAgent` and `VectorStore` capabilities. When these agents evaluate LLM-generated tool messages with `full_eval=True`, they attempt to sandbox the execution by explicitly setting `locals` to an empty dictionary `{}` inside Python's `eval()` function. However, this relies on an incomplete understanding of Python's execution model. Because `__builtins__` is not explicitly scrubbed from the `globals` dictionary mapping, Python implicitly injects all built-ins during execution, granting full access to functions like `__import__('os').system()`. Since `TableChatAgent.pandas_eval()` executes external LLM outputs natively, this bypass permits any attacker providing prompt payload to achieve unauthenticated RCE on the host system. Version 0.65.2 patches the issue.
How severe is CVE-2026-54769?
CVE-2026-54769 has a CVSS score of 10/10 (CRITICAL severity). The EPSS model estimates a 0.91% probability of exploitation in the next 30 days.
How do I fix CVE-2026-54769?
Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.

How Strix Helps

Related CVEs from 2026

Are you affected by CVE-2026-54769?

Run a free Strix scan to check your systems for this vulnerability.

Scan your code now

Source: NVD / NIST