CVE-2026-56075

published 18 Jun 2026 · updated 8 Nov 2026

PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override

8.8HighCVSS 8.8EPSS 1%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 1%. Fixed in 4.5.128.

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.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
PraisonAI<4.5.1284.5.128

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-56075 severity on Zeptric[![CVE-2026-56075](https://zeptric.io/badge/cve/CVE-2026-56075.svg)](https://zeptric.io/cve/CVE-2026-56075)