CVE-2026-54769
CVE-2026-54769 is a critical-severity vulnerability with a CVSS 3.x base score of 10.0. The underlying weakness is classified as CWE-94.
Key facts
- Severity: Critical (CVSS 3.x base score 10.0)
- Actively exploited: Not listed in CISA KEV
- Weakness: CWE-94
- Published:
- Last modified:
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.
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 3.x base score of 10.0, rated critical severity. It is exploitable over network with low attack complexity, requires no privileges and no user interaction. Impact on confidentiality is high, integrity high, and availability high.
- Is CVE-2026-54769 being actively exploited?
- It is not currently listed in CISA's Known Exploited Vulnerabilities catalog, and no EPSS exploit-prediction score is available yet.
- How do I fix CVE-2026-54769?
- Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its critical severity, prioritise patching exposed systems.
- When was CVE-2026-54769 published?
- CVE-2026-54769 was published on 2026-07-10.
References
Other CWE-94 (Code Injection) vulnerabilities
- CVE-2026-57624 — Critical (CVSS 10.0): Unauthenticated Remote Code Execution (RCE) in Blocksy Companion Pro <= 2.1.46 versions.
- CVE-2026-10134 — Critical (CVSS 10.0): IBM Langflow OSS 1.0.0 through 1.9.3 allows an attacker to read every secret available to the Langflow process, read…
- CVE-2026-53576 — Critical (CVSS 10.0): Kestra is an open-source, event-driven orchestration platform. Prior to 1.0.45 and 1.3.21, the authentication filter…
- CVE-2026-10561 — Critical (CVSS 10.0): IBM Langflow OSS 1.0.0 through 1.9.3 has an vulnerability due to an improper isolation of Python execution combined…
- CVE-2026-25470 — Critical (CVSS 10.0): Improper Control of Generation of Code ('Code Injection') vulnerability in ACPT ACPT (Pro) - Custom Post Types Plugin…
- CVE-2026-48836 — Critical (CVSS 10.0): Unauthenticated Remote Code Execution (RCE) in Easy Invoice <= 2.1.19 versions.