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 Executio

criticalCVSS 10CVE-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.

Details

Source: NVD Recent CVEs (US · database · site)
Severity: critical — CVSS 10
Published: 2026-07-10
Last updated: 2026-07-10
Exploitation: Not in CISA KEV at last sync

Original advisory: https://nvd.nist.gov/vuln/detail/CVE-2026-54769

Exploitation outlook

EPSS (FIRST.org) estimates each CVE’s probability of exploitation in the next 30 days — here is the CSIRTS.com read on those numbers.

Low exploitation riskCVE-2026-547690.91% 30-day exploitation probability — currently an unlikely target, but scores change as exploit code circulates. Riskier than 56% of all scored CVEs.

Referenced CVEs

CVE	CSIRTS overview	External
CVE-2026-54769	coverage & exploitation status	NVD · CVE.org

Same CVEs, other sources

How other CERTs, PSIRTs and databases cover the vulnerabilities in this advisory.

criticalGHSA-q9p7-wqxg-mrhc: Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in T…ghsa

Recent advisories for Langroid is a

A cluster of recent advisories against the same product widens the attack surface — attackers routinely chain freshly published CVEs on one product, so review these together.

unknownCVE-2026-55615: Langroid is a framework for building large-language-model-powered applications. Prior to versi…nvd · 2026-07-10
highCVE-2026-54771: Langroid is a framework for building large-language-model-powered applications. Prior to versi…nvd · 2026-07-10
unknownCVE-2026-54760: Langroid is a framework for building large-language-model-powered applications. Prior to versi…nvd · 2026-07-10
highCVE-2026-50181: Langroid is a framework for building large-language-model-powered applications. Prior to versi…nvd · 2026-07-10
unknownCVE-2026-50180: Langroid is a framework for building large-language-model-powered applications. Prior to versi…nvd · 2026-07-10
criticalGHSA-2pq5-3q89-j7cc: Langroid: Neo4jChatAgent executes LLM-generated Cypher without validation (prompt-to-Cyph…ghsa · 2026-07-06