---
title: "CVE-2026-54760: Langroid: SQLChatAgent dangerous-function blocklist can be bypassed with quoted or schema-qualified pg_read_file calls"
url: https://erroneo.us/security/cve/CVE-2026-54760/
description: "CVE-2026-54760 (langroid (PyPI)): Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.1, the SQLChatAgent…"
type: vulnerability-record
section: "Security Digest"
date_published: 2026-07-09
date_modified: 2026-07-10
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2026-54760"
kev: false
cvss: 9.3
epss: 0.00646
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2026-54760: Langroid: SQLChatAgent dangerous-function blocklist can be bypassed with quoted or schema-qualified pg_read_file calls

**Signal:** Critical and remotely reachable. No known exploitation yet, but it is network-reachable without credentials. (Computed from CISA KEV, EPSS and CVSS; not an editorial verdict.)

## Should you act?

- Not in CISA KEV , but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 0.6% , percentile 50: FIRST’s model estimates a 0.6% chance of exploitation activity in the next 30 days, higher than 50% 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) <= 0.65.0, fixed in 0.65.1 . Check your lockfile, including transitive dependencies.

## What it is

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.1, the SQLChatAgent SQL-injection mitigation, with default allowdangerousoperations=False, combines a raw-text regex blocklist (DANGEROUSSQLPATTERNS) with a sqlglot SELECT-only statement allowlist. The blocklist entries that target callable functions require the function name to be immediately followed by \s\(. PostgreSQL accepts the same call with the name separated from ( by a quoted identifier, an inline comment, or schema qualification. These forms evade the regex, still parse as SELECT, and execute the same PostgreSQL function. This restores the pgreadfile server-side file-read primitive that the prior CVE-2026-25879 / GHSA-pmch-g965-grmr fix was meant to block: the parent advisory fixed a missing pgreadfile blocklist entry, while this report shows that the added regex is bypassable. Version 0.65.1 fixes the issue.

## Affected packages

- PyPI `langroid` <= 0.65.0 → fixed: 0.65.1

## Affected products (CVE record)

- langroid langroid: < 0.65.1

## Severity

- GitHub_M CVSS 4.0: 9.3 `CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N`
- GitHub CVSS 4.0: 9.3 `CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N`

## Exploitation

- 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): 0.65% probability of exploitation activity in the next 30 days; percentile 50.

## Sources

- [GitHub Advisory GHSA-6xc5-4r68-67fc](https://github.com/advisories/GHSA-6xc5-4r68-67fc)
- [CVE.org record CVE-2026-54760](https://www.cve.org/CVERecord?id=CVE-2026-54760)
- [NVD entry CVE-2026-54760](https://nvd.nist.gov/vuln/detail/CVE-2026-54760)
- [github.com](https://github.com/langroid/langroid/security/advisories/GHSA-6xc5-4r68-67fc)

---
Source page: https://erroneo.us/security/cve/CVE-2026-54760/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt