EUVD-2026-36324

OpenClaw: MCP loopback could skip owner-only tool policy for non-owner callers...

PYSEC-2026-487 PraisonAIAgents has an OS Command Injection via shell=True in Memory Hooks Executor (memory/hooks.py)

Summary The memory hooks executor in praisonaiagents passes a user-controlled command string directly to subprocess.run with shell=True at src/praisonai-agents/praisonaiagents/memory/hooks.py lines 303 to 305. No sanitization, no shlex.quote, no character filter, and no allowlist check exists...

GHSA-68XW-R643-9P5W OpenClaw: Skill-command dispatch could skip before-tool-call hooks

Summary Skill-command dispatch could skip before-tool-call hooks. In affected versions, a skill command routed through the affected dispatch path could run without the same runBeforeToolCallHook coverage as other tool entry points. This advisory is scoped to the named feature and configuration. I...

CVE-2026-53845

OpenClaw prior to version 2026.5.6 has a hook bypass in the skill-command dispatch path, where commands routed through the affected path skip the before-tool-call hook coverage, potentially bypassing auditing and policy enforcement. This is described in the CVE entry as a dispatch hook bypass vul...

CVE-2026-53818

OpenClaw CVE-2026-53818 affects OpenClaw prior to 2026.4.24. It describes an authorization bypass in the MCP loopback feature that lets non-owner callers skip owner-only tool policies and before-tool-call hooks, potentially causing invocation of owner-only behavior to execute restricted tools whe...

PT-2026-48748

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.4.24 Description An authorization bypass exists in the MCP loopback feature. This allows non-owner callers to circumvent owner-only tool policies and before-tool-call hooks. When the feature is enabled and...

EUVD-2026-21152

PraisonAIAgents has an OS Command Injection via shell=True in Memory Hooks Executor memory/hooks.py...

CVE-2026-40111

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, he memory hooks executor in praisonaiagents passes a user-controlled command string directly to subprocess.run with shell=True at src/praisonai-agents/praisonaiagents/memory/hooks.py. No sanitization is performed and shell...

CVE-2026-40111 PraisonAIAgents has an OS Command Injection via shell=True in Memory Hooks Executor (memory/hooks.py)

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, he memory hooks executor in praisonaiagents passes a user-controlled command string directly to subprocess.run with shell=True at src/praisonai-agents/praisonaiagents/memory/hooks.py. No sanitization is performed and shell...

CVE-2026-40111

PraisonAIAgents memory/hooks.py allows OS command injection via a user-controlled string passed to subprocess.run() with shell=True before 1.5.128. No sanitization occurs, shell metacharacters are interpreted by /bin/sh, enabling execution of arbitrary commands. Two attack surfaces exist: pre_run...