Signal is active with 1 mentions in latest observed window
Recommended action window: Monitor and triage in normal cycle
NVD description
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'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.
Priority
LOW
Exploitation
NONE
PoC
NONE
Patch
AVAILABLE
Momentum
STABLE
| Date | Total | Labels |
|---|
| 2026-06-01 | 1 | Disclosure1 |
| 2026-06-02 | 1 | Disclosure1 |
| 2026-06-07 | 1 | Disclosure1 |
| 2026-06-22 | 1 | General1 |
| 2026-07-23 | 1 | Disclosure1 |
CVE-2026-25879: Langroid SQLChatAgent Prompt Injection Vulnerability - What It Means for Your Business and How to Respond https://hubs.li/Q04m95jW0
Post summary
The provided text is a headline linking to a resource that presumably discusses a prompt injection vulnerability in Langroid SQLChatAgent, but offers no additional technical specifics, exploit information, or mitigation guidance.
🚨 CRITICAL: CVE-2026-25879 (CVSS 9.8) Langroid SQLChatAgent vulnerable to SQL injection via LLM prompt manipulation → RCE on database hosts (PostgreSQL/MySQL/MSSQL). Fixed in v0[.]63[.]0. Patch immediately. #CVE #Vulnerability #PatchNow https://t.co/QY9J7Dcg23
Post summary
The post announces CVE‑2026‑25879, a SQL injection vulnerability in Langroid SQLChatAgent, provides technical details, and urges users to promptly patch with v0.63.0.
CVE-2026-25879 - Critical Code Execution in Langroid. SQLChatAgent executes LLM-generated SQL, enabling prompt injection attacks to run OS commands via database roles. CVSS 9.8. No patch available. Mitigate now. #CVE #Langroid #infosec #CVEAlert FREE https://www.valtersit.com/cve/CVE-2026-25879
Post summary
The post announces CVE‑2026‑25879, a critical code‑execution vulnerability in Langroid’s SQLChatAgent that allows prompt injection to execute OS commands, with a CVSS of 9.8 and no patch available, urging mitigation.
CVE-2026-25879 (Langroid SQLChatAgent) is a critical prompt-injection flaw. In high-risk configurations, LLM-generated SQL could enable code execution on database hosts. See full analysis: https://github.com/alan-turing-institute/cyber-threat-observatory/blob/main/reports/2026-06-01/TIER_2_CVE-2026-25879.md #CyberSecurity #DPI #AIsecurity #LLMSecurity #DatabaseSecurity
Post summary
The post announces CVE-2026-25879, describing a critical prompt‑injection vulnerability that could let LLM‑generated SQL enable code execution on database hosts, alongside a link to a detailed GitHub analysis.
CVE-2026-25879 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 influe… https://www.cve.org/CVERecord?id=CVE-2026-25879
Post summary
CVE-2026-25879 exposes a vulnerability in Langroid’s SQLChatAgent, enabling execution of SQL generated by an LLM prior to version 0.63.0; no PoC, exploit, patch, or active exploitation is reported.