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.
Published:Jun 18, 2026
Last Modified:Jun 22, 2026
EPS:Jun 18, 2026
EPSS Score:
CVSS Score:8.8
Affected Products
Vendor
Product
Action
Vendor
Praison
Product
Praisonai
Praison
Praisonai
Exploits
No exploit reference
Common Weakness Enumeration
Common Attack Pattern Enumeration and Classification (CAPEC)
No CAPEC recorded yet
Related CVEs
Common Vulnerability Scoring System
Attack Vector
Network
Adjacent
Local
Physical
Privileges Required
None
Low
High
User Interaction
None
Required
Scope
Unchanged
Changed
Confidentiality
None
Low
High
Integrity
None
Low
High
Availability
None
Low
High
