PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override
PraisonAI
Affected versions
| Product | Affected | Fixed in |
|---|---|---|
| praisonai PyPI |
|
|
Original 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.
From the CVE record · VulnCheck