Security audit

multi-clawd

Security checks for vulnerabilities and agentic risk

Overview

This package is a disclosed OpenClaw plugin for routing Claude Code work across user-configured Claude accounts, with expected credential handling and optional local watchdog persistence.

Before installing, confirm you want this plugin to handle Claude account credentials and route Claude Code launches across those accounts. Prefer secret references or chmod 600 token files, use dry-run for setup and Hermes sync, and only enable the watchdog if you are comfortable with a local timer that can restart the OpenClaw gateway.

SkillSpector

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/shim.js:90
Evidence: const child = spawn(command, childArgs, {

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: dist/watchdog-schedule.js:112
Evidence: const r = spawnSync(process.execPath, [script], { stdio: "inherit" });

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/cli.mjs:81
Evidence: const r = spawnSync(process.execPath, [join(__dirname, script), ...args], { stdio: "inherit" });

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: scripts/hermes.mjs:181
Evidence: const probe = spawnSync(python, ["-c", probeCode], {