CVE-2026-56075 | PraisonAI before 4.5.128 contains an arbitrary shell command… | CVSS 8.8 HIGH

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.

Metadata

CVE ID: CVE-2026-56075
State: PUBLISHED
Assigner: VulnCheck
Reserved: 2026-06-18 15:57 UTC
Published: 2026-06-18 22:12 UTC
Last updated: 2026-06-18 22:12 UTC
Primary CWE: CWE-863
Incorrect Authorization
Vendor / Product: PraisonAI / PraisonAI
Sources: cve.org · NVD

Severity & Metrics

8.8 HIGH CVSS 3.1

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Affected products (1)

Vendor	Product	Platform	Versions
PraisonAI	PraisonAI	—	0 < 4.5.128, 4.5.128

Weakness (CWE)

CWE	Source	Description
CWE-863	cna	Incorrect Authorization

CVSS scores (2)

Score	Severity	Version	Source	Vector
8.8	HIGH	3.1	cna	CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
8.7	HIGH	4.0	cna	CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

References (2)

GHSA Advisory GHSA-qwgj-rrpj-75xm https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-qwgj-rrpj-75xm
VulnCheck Advisory: PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override https://www.vulncheck.com/advisories/praisonai-arbitrary-shell-command-execution-via-hardcoded-approval-mode-override