<?xml version='1.0' encoding='UTF-8'?>
<?xml-stylesheet href="/static/style.xsl" type="text/xsl"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/" version="2.0">
  <channel>
    <title>Most recent entries from all</title>
    <link>https://cve.radiocsirt.org</link>
    <description>Contains only the most 10 recent entries.</description>
    <docs>http://www.rssboard.org/rss-specification</docs>
    <generator>python-feedgen</generator>
    <language>en</language>
    <lastBuildDate>Fri, 02 Oct 2026 23:23:50 +0000</lastBuildDate>
    <item>
      <title>CVE-2026-25879 — Langroid has Prompt to SQL Injection, Leading to RCE</title>
      <link>https://cve.radiocsirt.org/vuln/cve-2026-25879</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; langroid&lt;/p&gt;
&lt;p&gt;Langroid is a framework for building large-language-model-powered applications. Prior to version 0.63.0, SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database role that has privileges enabling code execution or filesystem access (e.g., PostgreSQL pg_execute_server_program, MySQL FILE, MSSQL xp_cmdshell), an attacker who can shape the agent&amp;#39;s input — including indirectly via data returned to the LLM — can coerce execution of dialect-specific primitives such as `COPY ... FROM PROGRAM`, achieving RCE on the database host. Fixed in v0.63.0 by defaulting SQLChatAgent to a SELECT-only sqlglot-parsed statement allowlist with a dialect-aware dangerous-pattern blocklist; allow_dangerous_operations=True restores the previous unrestricted behavior for trusted deployments.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; langroid&lt;/p&gt;
&lt;p&gt;Langroid is a framework for building large-language-model-powered applications. Prior to version 0.63.0, SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database role that has privileges enabling code execution or filesystem access (e.g., PostgreSQL pg_execute_server_program, MySQL FILE, MSSQL xp_cmdshell), an attacker who can shape the agent&amp;#39;s input — including indirectly via data returned to the LLM — can coerce execution of dialect-specific primitives such as `COPY ... FROM PROGRAM`, achieving RCE on the database host. Fixed in v0.63.0 by defaulting SQLChatAgent to a SELECT-only sqlglot-parsed statement allowlist with a dialect-aware dangerous-pattern blocklist; allow_dangerous_operations=True restores the previous unrestricted behavior for trusted deployments.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/cve-2026-25879</guid>
    </item>
    <item>
      <title>GHSA-mxfr-6hcw-j9rq — Langroid has Prompt to SQL Injection, Leading to RCE</title>
      <link>https://cve.radiocsirt.org/vuln/ghsa-mxfr-6hcw-j9rq</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: langroid&lt;/p&gt;
&lt;p&gt;# Security Vulnerability Report: Prompt to SQL Injection leading to RCE in latest Langroid&lt;/p&gt;
&lt;p&gt;## Affected Scope
langroid &amp;lt; 0.63.0&lt;/p&gt;
&lt;p&gt;## Vulnerability Description&lt;/p&gt;
&lt;p&gt;SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database role that has privileges enabling code execution or filesystem access (e.g., PostgreSQL pg_execute_server_program, MySQL FILE, MSSQL xp_cmdshell), an attacker who can shape the agent&amp;#39;s input — including indirectly via data returned to the LLM — can coerce execution of dialect-specific primitives such as `COPY ... FROM PROGRAM`, achieving RCE on the database host. Fixed in vX.Y by defaulting SQLChatAgent to a SELECT-only sqlglot-parsed statement allowlist with a dialect-aware dangerous-pattern blocklist; allow_dangerous_operations=True restores the previous unrestricted behavior for trusted deployments.&lt;/p&gt;
&lt;p&gt;## Reproduction &amp;amp; PoC&lt;/p&gt;
&lt;p&gt;This demo can be used to reproduce the vulnerability:&lt;/p&gt;
&lt;p&gt;```python
&amp;#34;&amp;#34;&amp;#34;Minimal PostgreSQL Chat Demo using Langroid&amp;#34;&amp;#34;&amp;#34;&lt;/p&gt;
&lt;p&gt;import base64
import os
from langroid.agent.special.sql.sql_chat_agent import SQLChatAgent, SQLChatAgentConfig
from langroid.agent.task import Task
from langroid.language_models.openai_gpt import OpenAIGPTConfig&lt;/p&gt;
&lt;p&gt;# Use personal PostgreSQL connection string
DATABASE_URI = &amp;#34;postgresql://postgres:&amp;lt;pass&amp;gt;@localhost:5432/postgres&amp;#34;&lt;/p&gt;
&lt;p&gt;# Create SQL Chat Agent
config = SQLChatAgentConfig(
    database_uri=DATABASE_URI,
    llm=OpenAIGPTConfig(
        api_base=os.getenv(&amp;#34;ba…&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: langroid&lt;/p&gt;
&lt;p&gt;# Security Vulnerability Report: Prompt to SQL Injection leading to RCE in latest Langroid&lt;/p&gt;
&lt;p&gt;## Affected Scope
langroid &amp;lt; 0.63.0&lt;/p&gt;
&lt;p&gt;## Vulnerability Description&lt;/p&gt;
&lt;p&gt;SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database role that has privileges enabling code execution or filesystem access (e.g., PostgreSQL pg_execute_server_program, MySQL FILE, MSSQL xp_cmdshell), an attacker who can shape the agent&amp;#39;s input — including indirectly via data returned to the LLM — can coerce execution of dialect-specific primitives such as `COPY ... FROM PROGRAM`, achieving RCE on the database host. Fixed in vX.Y by defaulting SQLChatAgent to a SELECT-only sqlglot-parsed statement allowlist with a dialect-aware dangerous-pattern blocklist; allow_dangerous_operations=True restores the previous unrestricted behavior for trusted deployments.&lt;/p&gt;
&lt;p&gt;## Reproduction &amp;amp; PoC&lt;/p&gt;
&lt;p&gt;This demo can be used to reproduce the vulnerability:&lt;/p&gt;
&lt;p&gt;```python
&amp;#34;&amp;#34;&amp;#34;Minimal PostgreSQL Chat Demo using Langroid&amp;#34;&amp;#34;&amp;#34;&lt;/p&gt;
&lt;p&gt;import base64
import os
from langroid.agent.special.sql.sql_chat_agent import SQLChatAgent, SQLChatAgentConfig
from langroid.agent.task import Task
from langroid.language_models.openai_gpt import OpenAIGPTConfig&lt;/p&gt;
&lt;p&gt;# Use personal PostgreSQL connection string
DATABASE_URI = &amp;#34;postgresql://postgres:&amp;lt;pass&amp;gt;@localhost:5432/postgres&amp;#34;&lt;/p&gt;
&lt;p&gt;# Create SQL Chat Agent
config = SQLChatAgentConfig(
    database_uri=DATABASE_URI,
    llm=OpenAIGPTConfig(
        api_base=os.getenv(&amp;#34;ba…&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://cve.radiocsirt.org/vuln/ghsa-mxfr-6hcw-j9rq</guid>
    </item>
  </channel>
</rss>
