CVE-2026-56075
HIGH
MEDIUM
Priority: 0.05
BB Relevance:
68/100
Published: 2026-06-18
Modified: 2026-11-08
First seen: 2026-11-08
Status: active
Attack Surface
Network
Low Complexity
No Interaction
Conf. Impact
Integ. Impact
CVSS Vector Breakdown
AV:
Network
AC:
Low
PR:
Low
UI:
None
AT:
None
VC:
High
VI:
High
VA:
High
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.
Weakness Classification (1)
References & Advisories (2)
vendor-advisory
third-party-advisory