CVE-2026-56075
HIGH EPSS 37.6%
Published Jun 18, 20261w ago · Modified Jun 22, 20261w ago
8.7 CVSS 4.0
Published Jun 18, 2026 1w ago
Last Modified Jun 22, 2026 1w ago
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.
CVSS Details
Base Score
Exploitability
Impact
Vector string
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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X Attack Vector Network
Attack Complexity Low
Privileges Required Low
User Interaction None
Scope X
Threat Intelligence
EPSS Exploit Probability
37.6% percentile
Exploit & Patch Status
No Known Exploit
No Patch Available
Weaknesses 1
CWE-863 Incorrect Authorization Authorization
References 2
- github.com https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-qwgj-rrpj-75xm
- vulncheck.com https://www.vulncheck.com/advisories/praisonai-arbitrary-shell-command-execution-via-hardcoded-approval-mode-override
Remediation
No remediation data recorded yet
Check vendor advisories and the NVD entry for patch availability.