{"api_version":"1","generated_at":"2026-07-10T14:04:34+00:00","cve":"CVE-2026-54769","urls":{"html":"https://cve.report/CVE-2026-54769","api":"https://cve.report/api/cve/CVE-2026-54769.json","docs":"https://cve.report/api","cve_org":"https://www.cve.org/CVERecord?id=CVE-2026-54769","nvd":"https://nvd.nist.gov/vuln/detail/CVE-2026-54769"},"summary":{"title":"Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent","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.","state":"PUBLISHED","assigner":"GitHub_M","published_at":"2026-07-10 00:16:33","updated_at":"2026-07-10 00:16:33"},"problem_types":["CWE-94","CWE-94 CWE-94: Improper Control of Generation of Code ('Code Injection')"],"metrics":[{"version":"3.1","source":"security-advisories@github.com","type":"Secondary","score":"10","severity":"CRITICAL","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","data":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","baseScore":10,"baseSeverity":"CRITICAL","attackVector":"NETWORK","attackComplexity":"LOW","privilegesRequired":"NONE","userInteraction":"NONE","scope":"CHANGED","confidentialityImpact":"HIGH","integrityImpact":"HIGH","availabilityImpact":"HIGH"}},{"version":"3.1","source":"CNA","type":"DECLARED","score":"10","severity":"CRITICAL","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","data":{"attackComplexity":"LOW","attackVector":"NETWORK","availabilityImpact":"HIGH","baseScore":10,"baseSeverity":"CRITICAL","confidentialityImpact":"HIGH","integrityImpact":"HIGH","privilegesRequired":"NONE","scope":"CHANGED","userInteraction":"NONE","vectorString":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","version":"3.1"}}],"references":[{"url":"https://github.com/langroid/langroid/security/advisories/GHSA-q9p7-wqxg-mrhc","name":"https://github.com/langroid/langroid/security/advisories/GHSA-q9p7-wqxg-mrhc","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-54769","name":"CVE Program record","refsource":"CVE.ORG","tags":["canonical"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-54769","name":"NVD vulnerability detail","refsource":"NVD","tags":["canonical","analysis"]}],"affected":[{"source":"CNA","vendor":"langroid","product":"langroid","version":"affected < 0.65.2","platforms":[]}],"timeline":[],"solutions":[],"workarounds":[],"exploits":[],"credits":[],"nvd_cpes":[],"vendor_comments":[],"enrichments":{"kev":null,"epss":null,"legacy_qids":[]},"source_records":{"cve_program":{"containers":{"cna":{"affected":[{"product":"langroid","vendor":"langroid","versions":[{"status":"affected","version":"< 0.65.2"}]}],"descriptions":[{"lang":"en","value":"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":[{"cvssV3_1":{"attackComplexity":"LOW","attackVector":"NETWORK","availabilityImpact":"HIGH","baseScore":10,"baseSeverity":"CRITICAL","confidentialityImpact":"HIGH","integrityImpact":"HIGH","privilegesRequired":"NONE","scope":"CHANGED","userInteraction":"NONE","vectorString":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","version":"3.1"}}],"problemTypes":[{"descriptions":[{"cweId":"CWE-94","description":"CWE-94: Improper Control of Generation of Code ('Code Injection')","lang":"en","type":"CWE"}]}],"providerMetadata":{"dateUpdated":"2026-07-09T23:51:10.855Z","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","shortName":"GitHub_M"},"references":[{"name":"https://github.com/langroid/langroid/security/advisories/GHSA-q9p7-wqxg-mrhc","tags":["x_refsource_CONFIRM"],"url":"https://github.com/langroid/langroid/security/advisories/GHSA-q9p7-wqxg-mrhc"}],"source":{"advisory":"GHSA-q9p7-wqxg-mrhc","discovery":"UNKNOWN"},"title":"Langroid: Sandbox Escape to Remote Code Execution via Incomplete `eval()` Mitigation in TableChatAgent"}},"cveMetadata":{"assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","assignerShortName":"GitHub_M","cveId":"CVE-2026-54769","datePublished":"2026-07-09T23:51:10.855Z","dateReserved":"2026-06-15T23:23:57.713Z","dateUpdated":"2026-07-09T23:51:10.855Z","state":"PUBLISHED"},"dataType":"CVE_RECORD","dataVersion":"5.2"},"nvd":{"publishedDate":"2026-07-10 00:16:33","lastModifiedDate":"2026-07-10 00:16:33","problem_types":["CWE-94","CWE-94 CWE-94: Improper Control of Generation of Code ('Code Injection')"],"metrics":{"cvssMetricV31":[{"source":"security-advisories@github.com","type":"Secondary","cvssData":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","baseScore":10,"baseSeverity":"CRITICAL","attackVector":"NETWORK","attackComplexity":"LOW","privilegesRequired":"NONE","userInteraction":"NONE","scope":"CHANGED","confidentialityImpact":"HIGH","integrityImpact":"HIGH","availabilityImpact":"HIGH"},"exploitabilityScore":3.9,"impactScore":6}]},"configurations":[]},"legacy_mitre":{"record":{"CveYear":"2026","CveId":"54769","Ordinal":"1","Title":"Langroid: Sandbox Escape to Remote Code Execution via Incomplete","CVE":"CVE-2026-54769","Year":"2026"},"notes":[{"CveYear":"2026","CveId":"54769","Ordinal":"1","NoteData":"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.","Type":"Description","Title":"Langroid: Sandbox Escape to Remote Code Execution via Incomplete"}]}}}