{"cve":"CVE-2026-54769","nvd":{"published":"2026-07-10T00:16:33.603","modified":"2026-07-10T15:49:19.093","status":"Deferred","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.","cvss_v4":null,"cvss_v3":{"version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","score":10.0},"cwes":["CWE-94"],"references":["https://github.com/langroid/langroid/security/advisories/GHSA-q9p7-wqxg-mrhc","https://github.com/langroid/langroid/security/advisories/GHSA-q9p7-wqxg-mrhc"],"products":[],"source":"nvd","synced_at":"2026-10-19T22:44:02.134301115+00:00"},"epss":{"cve":"CVE-2026-54769","score":0.00912,"percentile":0.60048,"date":"2026-11-01"},"kev":null,"osv":[{"id":"GHSA-q9p7-wqxg-mrhc","url":"https://osv.dev/vulnerability/GHSA-q9p7-wqxg-mrhc","summary":"Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent","modified":"2026-07-13T16:43:21.984122629Z","packages":[{"ecosystem":"PyPI","name":"langroid","purl":"pkg:pypi/langroid","ranges":["<0.65.2"],"fixed":["0.65.2"]}]},{"id":"PYSEC-2026-2581","url":"https://osv.dev/vulnerability/PYSEC-2026-2581","summary":"Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent","modified":"2026-07-13T16:31:59.875373128Z","packages":[{"ecosystem":"PyPI","name":"langroid","purl":"pkg:pypi/langroid","ranges":["<0.65.2"],"fixed":["0.65.2"]}]}],"attribution":["This product uses the NVD API but is not endorsed or certified by the NVD.","EPSS scores: FIRST Exploit Prediction Scoring System, https://www.first.org/epss","Known exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog, https://www.cisa.gov/known-exploited-vulnerabilities-catalog","Package advisories: OSV (https://osv.dev), from the GitHub Advisory Database, PyPA, Go, RustSec and other ecosystem databases, under CC-BY 4.0 or CC0","CVE records: the CVE Program's CVE List (https://www.cve.org), under its terms of use (https://www.cve.org/Legal/TermsOfUse). CVE is a registered trademark of The MITRE Corporation; this product is not affiliated with the CVE Program."]}