← Back to CVE List
Vulnerability Analysis
Langroid has Prompt to SQL Injection, Leading to RCE

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 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.

No Active Exploit Signals
CVSS Base Score
9.8
CRITICAL
Exploitability:3.9
Impact Score:5.9
Temporal Score:-
EPSS:0.41%

Threat Intelligence Signals

CISA KEV
No
KEV Date Added
Ransomware Use
KEV Due Date
VulnCheck In-the-Wild
No
Nuclei Template
No
EPSS Score
0.409%
EPSS Percentile
32.5th pct
GitHub Severity
CRITICAL
SSVC Exploitation
SSVC Automatable
Vulnerability Class

Identity & Timeline

Status-
Assigning Authority-
CVSS Version / Source-
Reserved-
Published-
Patch Date (date_public)-
Exploit DB Date-
First GitHub PoC Date-
Last Updated-
Time to Patch (Days to fix)-
Exploit Release Gap-
PoC Release Gap-
Exploit DB ReferencesNone identified

Affected Products & Versions

Vendor Product Affected Versions
No affected products specified.

References

No reference links found.

LINK COPIED TO CLIPBOARD