Vulnerability  ·  2026-06-20

PraisonAI Hardcoded approval_mode:auto Allows Authenticated Users to Execute Arbitrary Shell Commands (CVSS 8.8)

VulnerabilityHigh impactGlobalCVE-2026-56075
PraisonAI's UI modules hardcode approval_mode to 'auto', ignoring the administrator's PRAISON_APPROVAL_MODE environment variable configuration. This means any authenticated user can direct the LLM agent to execute arbitrary shell commands via subprocess.run with shell=True, bypassing the manual approval gate designed to prevent unauthorized command execution. Published 2026-06-18, CVSS 8.8 HIGH.
In AI agent deployments, approval gates are a primary safety control preventing agents from taking destructive actions. Hardcoding auto-approval completely nullifies administrator-configured human oversight for shell execution — a core agentic security control — allowing lateral movement, data exfiltration, or full host compromise from any authenticated session.
Authenticated attacker instructs the LLM agent via the UI to run a shell command. The UI module hardcodes approval_mode=auto, overriding the administrator-set PRAISON_APPROVAL_MODE environment variable that would require manual approval. The agent executes the command via subprocess.run(shell=True) with insufficient blocklist sanitization.
PraisonAI < 4.5.128
Upgrade to PraisonAI 4.5.128 or later. Advisory: https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-qwgj-rrpj-75xm
Sources
NVD CVE-2026-56075GitHub Advisory GHSA-qwgj-rrpj-75xmVulnCheck Advisory — PraisonAI arbitrary shell command executionPT Security dbugs CVE-2026-56075
See this in the live feed Explore related AI security and governance findings — updated every morning.
Open the feed →