CVE-2026-56075highCWE-863

CVE-2026-56075: high-severity vulnerability in PraisonAI

PraisonAI - Arbitrary Shell Command Execution via Hardcoded Approval Mode Override

Published · Updated

Follow this CVE+ Monitor PraisonAI+ Monitor praisonai

E-mail alert when it lands in KEV, gets a public PoC or its score goes up.

21Vexday Risk Score

No sign of exploitation. No public exploitation artifact known so far.

ssvc Trackcvss 8.7epss 0.6%
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.
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Affected products
PraisonAI · PraisonAI
Related CVEs — PraisonAI

In the same product, most dangerous first.

CVE-2026-56078HIGHPraisonAI - Arbitrary File Read and Write via Path Traversal in MultiAgentMonitorEPSS 0.9%CVE-2026-56076HIGHPraisonAI - Cross-Origin Agent Execution via Hardcoded Wildcard CORS and Missing Authentication on AGUI EndpointEPSS 0.6%CVE-2026-56077HIGHPraisonAI - Information Disclosure via Shared MultiAgentLedger StateEPSS 0.4%CVE-2026-58653MEDIUMPraisonAI - Authorization Bypass via Unvalidated project_id in Issue Create/UpdateEPSS 0.3%CVE-2026-56074MEDIUMPraisonAI - Tool Approval Cache Bypass via Coarse-Grained CachingEPSS 0.2%