https://cve.radiocsirt.org Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Sat, 03 Oct 2026 09:06:51 +0000 https://cve.radiocsirt.org/vuln/cve-2025-46725 <p><strong>Affected:</strong> langroid</p> <p>Langroid is a Python framework to build large language model (LLM)-powered applications. Prior to version 0.53.15, `LanceDocChatAgent` uses pandas eval() through `compute_from_docs()`. As a result, an attacker may be able to make the agent run malicious commands through `QueryPlan.dataframe_calc]`) compromising the host system. Langroid 0.53.15 sanitizes input to the affected function by default to tackle the most common attack vectors, and added several warnings about the risky behavior in the project documentation.</p> <p><strong>Affected:</strong> langroid</p> <p>Langroid is a Python framework to build large language model (LLM)-powered applications. Prior to version 0.53.15, `LanceDocChatAgent` uses pandas eval() through `compute_from_docs()`. As a result, an attacker may be able to make the agent run malicious commands through `QueryPlan.dataframe_calc]`) compromising the host system. Langroid 0.53.15 sanitizes input to the affected function by default to tackle the most common attack vectors, and added several warnings about the risky behavior in the project documentation.</p> https://cve.radiocsirt.org/vuln/cve-2025-46725 https://cve.radiocsirt.org/vuln/ghsa-22c2-9gwg-mj59 <p><strong>Affected:</strong> PyPI: langroid</p> <p>### Summary [LanceDocChatAgent](https://github.com/langroid/langroid/blob/main/langroid/agent/special/lance_doc_chat_agent.py#L158) uses pandas eval() through `compute_from_docs()`: https://github.com/langroid/langroid/blob/18667ec7e971efc242505196f6518eb19a0abc1c/langroid/vector_store/base.py#L136-L150</p> <p>As a result, an attacker may be able to make the agent run malicious commands through [QueryPlan.dataframe_calc](https://github.com/langroid/langroid/blob/main/langroid/agent/special/lance_tools.py#L16) compromising the host system.</p> <p>### Fix Langroid 0.53.15 sanitizes input to the affected function by default to tackle the most common attack vectors, and added several warnings about the risky behavior in the project documentation.</p> <p><strong>Affected:</strong> PyPI: langroid</p> <p>### Summary [LanceDocChatAgent](https://github.com/langroid/langroid/blob/main/langroid/agent/special/lance_doc_chat_agent.py#L158) uses pandas eval() through `compute_from_docs()`: https://github.com/langroid/langroid/blob/18667ec7e971efc242505196f6518eb19a0abc1c/langroid/vector_store/base.py#L136-L150</p> <p>As a result, an attacker may be able to make the agent run malicious commands through [QueryPlan.dataframe_calc](https://github.com/langroid/langroid/blob/main/langroid/agent/special/lance_tools.py#L16) compromising the host system.</p> <p>### Fix Langroid 0.53.15 sanitizes input to the affected function by default to tackle the most common attack vectors, and added several warnings about the risky behavior in the project documentation.</p> https://cve.radiocsirt.org/vuln/ghsa-22c2-9gwg-mj59