LIVE · cybersecurity feed
Live wire
CVE-2026-81578 · PaperCut NG/MF Flaw Exploited Before CVE PublicationCVE-2026-82078 · PaperCut NG/MF Flaw Exploited Before CVE PublicationCVE-2026-83549 · SonicWall SMA1000 OS Command Injection Exploited Same Day as DisclosureCVE-2026-83548 · SonicWall SMA1000 SSRF Flaw Exploited Same Day as DisclosureCVE-2026-82329 · JFrog Artifactory Flaw Exploited Same Day as DisclosureOpenAI Announced $1B in Defensive Tools for Water UtilitiesAttackers Breached JetBrains Cadence via Unpatched TeamCity, Extracting AWS CredentialsCVE-2026-59346 · Critical VMware Workstation and Fusion Flaw Lets VM Admins Execute Host CodeCVE-2026-32475 · Elementor Pro WordPress Plugin Vulnerability Exploited to Hack SitesBroadcom Patches Critical VMware Workstation and Fusion VM-Escape Vulnerabilities
cve recordhigh

CVE-2026-56075

Published
CVSS8.8
Severityhigh
WeaknessCWE-863
ExploitedNot in CISA KEV

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

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.

References

← Back to the CVE Tracker

Our coverage of CVE-2026-56075

No stories yet. This page updates automatically when we publish reporting that references CVE-2026-56075.