Vulnerability · Published Jun 18, 2026 · Assigned by VulnCheck

CVE-2026-56075PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override

High 8.8

In plain English

A high-severity incorrect authorization in PraisonAI from PraisonAI. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 49% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)8.8High

Exploit odds (30 days)0.6%top 51.3% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official description

PraisonAI before 4.5.128 contains an arbitrary shell command execution vulnerability where the UI modules hardcode approval_mode to auto, overriding administrator configuration from PRAISON_APPROVAL_MODE environment variable. Authenticated attackers can instruct the LLM agent to execute arbitrary shell commands via subprocess.run with shell=True, bypassing the manual approval gate and insufficient command sanitization blocklists.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	praisonai	4.5.128	GHSA-qwgj-rrpj-75xm

Affected products (as reported)

Vendor	Product	Versions
PraisonAI	PraisonAI	0 – before 4.5.128

Weakness: CWE-863 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

References

GHSA Advisory GHSA-qwgj-rrpj-75xm vendor-advisory
VulnCheck Advisory: PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override third-party-advisory