CVE-2026-56075

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 4.0

8.7CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

CVSS 3.1

8.8CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

EPSS

0.6% chance of exploitation in the next 30 days; higher than 48% of CVEs (scores of 2026-10-25)

CWE

CWE-863

Published

2026-06-18

Modified

2026-10-08

Record from

the NVD, synced 2026-10-19

Packages (OSV)

References

• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-qwgj-rrpj-75xm
• https://www.vulncheck.com/advisories/praisonai-arbitrary-shell-command-execution-via-hardcoded-approval-mode-override
• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-qwgj-rrpj-75xm

Check your stackJSON