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...

CVE-2026-54760

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.1, the SQLChatAgent SQL-injection mitigation, with default allowdangerousoperations=False, combines a raw-text regex blocklist DANGEROUSSQLPATTERNS with a sqlglot SELECT-only statement allowlist...

CVE-2026-55615

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.5, Neo4jChatAgent passes LLM-generated Cypher queries straight to the Neo4j driver with no validation, no statement-type allowlist, and no opt-out gate. The query text is influenceable by prompt...

CVE-2026-54771

Langroid prior to 0.65.3 is affected. A Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with use=False, handle=True. Root cause: the tool dispatch path in agent_response → handle_message → get...

CVE-2026-54760

CVE-2026-54760: Langroid’s SQLChatAgent dangerous-function blocklist can be bypassed. Prior to version 0.65.1, the mitigation combines a raw-text regex (_DANGEROUS_SQL_PATTERNS) with a sqlglot-based SELECT-only allowlist. Attackers can defeat the regex using PostgreSQL forms such as quoted identi...

CVE-2026-50180

Summary: CVE-2026-50180 in Langroid’s SQLChatAgent allows arbitrary PostgreSQL file reads due to an incomplete DANGEROUS_SQL_PATTERNS blocklist. The blocklist misses several pg_read * and related functions (e.g., pg_read_file, pg_stat_file, pg_ls_logdir, pg_ls_waldir, pg_current_logfile) and does...

CVE-2026-55615

Langroid CVE-2026-55615 affects the Neo4jChatAgent path, where LLM-generated Cypher queries are sent unvalidated to the Neo4j driver prior to version 0.65.5. Connected docs describe a prompt-injection risk enabling read/write/destroy of graph data and, with APOC or dbms.security, potential OS com...

CVE-2026-25481

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.59.32, there is a bypass to the fix for CVE-2025-46724. TableChatAgent can call pandaseval tool to evaluate the expression. There is a WAF in langroid/utils/pandasutils.py introduced to block code...

CVE-2026-25481 Langroid has WAF Bypass Leading to RCE in TableChatAgent

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.59.32, there is a bypass to the fix for CVE-2025-46724. TableChatAgent can call pandaseval tool to evaluate the expression. There is a WAF in langroid/utils/pandasutils.py introduced to block code...

CVE-2026-25481 Langroid has WAF Bypass Leading to RCE in TableChatAgent

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.59.32, there is a bypass to the fix for CVE-2025-46724. TableChatAgent can call pandaseval tool to evaluate the expression. There is a WAF in langroid/utils/pandasutils.py introduced to block code...

EUVD-2025-13410

Malicious code in bioql PyPI...

CVE-2025-46724

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, TableChatAgent uses pandas eval. If fed by untrusted user input, like the case of a public-facing LLM application, it may be vulnerable to code injection. Langroid 0.53.15 sanitizes...

CVE-2025-46725 Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, LanceDocChatAgent uses pandas eval through computefromdocs. As a result, an attacker may be able to make the agent run malicious commands through QueryPlan.dataframecalc compromising t...

CVE-2025-46725 Langroid has a Code Injection vulnerability in LanceDocChatAgent through vector_store

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, LanceDocChatAgent uses pandas eval through computefromdocs. As a result, an attacker may be able to make the agent run malicious commands through QueryPlan.dataframecalc compromising t...

CVE-2025-46724 Langroid has a Code Injection vulnerability in TableChatAgent

Langroid is a Python framework to build large language model LLM-powered applications. Prior to version 0.53.15, TableChatAgent uses pandas eval. If fed by untrusted user input, like the case of a public-facing LLM application, it may be vulnerable to code injection. Langroid 0.53.15 sanitizes...

CVE-2025-46726

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.53.4, a LLM application leveraging XMLToolMessage class may be exposed to untrusted XML input that could result in DoS and/or exposing local files with sensitive information. Version 0.53.4 fixes th...

CVE-2025-46726

Langroid prior to 0.53.4 is vulnerable via the XMLToolMessage class to untrusted XML input, enabling DoS and potential disclosure of local files. The issue is mitigated by upgrading to version 0.53.4, which initializes the XML parser with safeguards against XXE, billionaire laughs, and external D...

CVE-2025-46726 Langroid Vulnerable to XXE Injection via XMLToolMessage

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.53.4, a LLM application leveraging XMLToolMessage class may be exposed to untrusted XML input that could result in DoS and/or exposing local files with sensitive information. Version 0.53.4 fixes th...