CVE-2026-56075
HIGHPraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override
Title source: cnaDescription
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.
References (2)
Core 2
Core References
Vendor Advisory vendor-advisory
GHSA Advisory GHSA-qwgj-rrpj-75xm
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-qwgj-rrpj-75xm
Third Party Advisory third-party-advisory
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
Scores
CVSS v3
8.8
EPSS
0.0048
EPSS Percentile
37.7%
Attack Vector
NETWORK
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
CISA SSVC
Vulnrichment
Exploitation
poc
Automatable
no
Technical Impact
total
Details
CWE
CWE-863
Status
published
Products (2)
PraisonAI/PraisonAI
< 4.5.128
PraisonAI/PraisonAI
4.5.128
Published
Jun 18, 2026
Tracked Since
Jun 19, 2026