Vulnerability record/PUBLISHED/Published Jun 18, 2026 22:12:23 UTC
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.
Base score8.7/ 10
SeverityHighCVSS 4.0
Exploitability / impact
CVSS metric breakdown
Base severityHigh
Attack vectorNetworkAV
Attack complexityLowAC
Attack requirementsNoneAT
Privileges requiredLowPR
User interactionNoneUI
Vulnerable system confidentialityHighVC
Vulnerable system integrityHighVI
Vulnerable system availabilityHighVA
Subsequent system confidentialityNoneSC
Subsequent system integrityNoneSI
Subsequent system availabilityNoneSA
CVSS 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:NCVSS communicates standardized severity and impact characteristics. It does not establish whether a system is exploitable in your specific environment.
Record context
CVE Numbering AuthorityVulnCheck
Last updatedNov 8, 2026 14:05:25 UTC
PublishedJun 18, 2026 22:12:23 UTC
ReservedJun 18, 2026 15:57:20 UTC
Credits
- offset