Back to plugin

Security audit

TinkerClaw Prefrontal

Security checks for vulnerabilities and agentic risk

Overview

This plugin is purpose-related orchestration software, but it exposes broad control paths that deserve manual review before installation.

Install only if you want this package to act as a high-authority orchestration layer for OpenClaw. Review who can call its gateway methods, avoid enabling untrusted recipe/script inputs, keep JourneyKits API keys scoped, and treat configured permission-hook scripts as local command execution with your user privileges.

SkillSpector was not run because this plugin release contains no bundled skills.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
dist/index.js:1563
Evidence
const output = execSync(hook.script, {