CVE-2026-5594Public exploitNetwork attack vector

Authenticated code execution via unsafe model-output eval

Published Apr 5, 2026 · Updated Apr 5, 2026

Code injection in Prem AI PremSQL 0.2.0 and 0.2.1 allows remote authenticated users to execute Python code through follow-up prompts. The BaseLineFollowupWorker passes a language model's raw result string, after only replacing JSON null tokens, to eval(), which interprets attacker-shaped model output as Python. Access to the self-hosted agent endpoint and control of a follow-up prompt are required; successful exploitation runs code with the PremSQL server process's privileges.

CVSS severity6.3
Medium
EPSS probability0.25%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Code injection in Prem AI PremSQL 0.2.0 and 0.2.1 allows remote authenticated users to execute Python code through follow-up prompts. The BaseLineFollowupWorker passes a language model's raw result string, after only replacing JSON null tokens, to eval(), which interprets attacker-shaped model output as Python. Access to the self-hosted agent endpoint and control of a follow-up prompt are required; successful exploitation runs code with the PremSQL server process's privileges.

The record

CVE
CVE-2026-5594
Published
Apr 5, 2026
Updated
Apr 5, 2026
Vendor
Prem AI
Product
PremSQL
Classifications
CWE-74, CWE-94, T1059.006
Attack vector
network
Privileges
authenticated

Timeline

How it unfolded

  1. Apr 5, 2026CVE publishedPublication date reported by the CVE source.
  2. Apr 5, 2026Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=0.2.0
  2. Affected versionversion=0.2.1

What conditions does exploitation require?

Attack vectornetwork
Required privilegesauthenticated

What is affected?

Prem AI · PremSQLversion=0.2.0; version=0.2.1

Published CVSS scores

6.5VulDBAV:N/AC:L/Au:S/C:P/I:P/A:P
6.3VulDBCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
2.1VulDBCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesauthenticated
Known exploitationUnconfirmed
Public exploitPublished

Weakness, pattern, technique

CWE-74Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')
CWE-94Improper Control of Generation of Code ('Code Injection')
T1059.006Python

Public exploit references

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo