CVE-2026-25879: Langroid has Prompt to SQL Injection, Leading to RCE

Should you act?

Critical and remotely reachable

No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.

• Not in CISA KEV, but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
• EPSS 0.7%, percentile 52: FIRST’s model estimates a 0.7% chance of exploitation activity in the next 30 days, higher than 52% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
• Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
• Only applies if your dependency tree includes langroid (PyPI) < 0.63.0, fixed in 0.63.0. Check your lockfile, including transitive dependencies.

What it is

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 pgexecuteserverprogram, MySQL FILE, MSSQL xpcmdshell), 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; allowdangerousoperations=True restores the previous unrestricted behavior for trusted deployments.

From the GitHub advisory

Security Vulnerability Report: Prompt to SQL Injection leading to RCE in latest Langroid

Affected Scope langroid

Vulnerability Description

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 pgexecuteserverprogram, MySQL FILE, MSSQL xpcmdshell), 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 vX.Y by defaulting SQLChatAgent to a SELECT-only sqlglot-parsed statement allowlist with a dialect-aware dangerous-pattern blocklist; allowdangerousoperations=True restores the previous unrestricted behavior for trusted deployments.

Reproduction & PoC

Weakness type: CWE-89, CWE-94.

Product: langroid (PyPI) · Assigned by: GitHub_M · Published: 2026-06-01

Affected and fixed versions

Severity scores

• Attack vector: network (remotely reachable)
• Attack complexity: low
• Privileges required: none (no login)
• User interaction: none
• Scope: unchanged

CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.

Exploitation and urgency

• CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
• CISA SSVC assessment: exploitation poc, automatable yes, technical impact total.
• FIRST EPSS (model of 2026-10-21): 0.69% probability of exploitation activity in the next 30 days; percentile 52.

Timeline

• 2026-05-27 — GitHub-reviewed advisory GHSA-mxfr-6hcw-j9rq published (critical)
• 2026-06-01 — CVE record published by GitHub_M
• 2026-06-02 — CVE record last updated

Sources and references

Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.

Vulnerability records

1. GitHub Advisory GHSA-mxfr-6hcw-j9rq github.com
2. CVE.org record CVE-2026-25879 cve.org
3. NVD entry CVE-2026-25879 nvd.nist.gov

Other references from the CVE record and advisory

1. github.com github.com
2. github.com github.com
3. pypi.org pypi.org

Critical PyPI advisories · Today’s Security Digest