Shell command execution detected (child_process).
Critical
- Code
- suspicious.dangerous_exec
- Location
- dist/index.js:983
- Evidence
log.info(`env for claude spawn (${Object.keys(cleanEnv).length} vars, names only): ${envKeys}`);
Security audit
Security checks across malware telemetry and agentic risk
This plugin is clearly a Claude Code bridge, but it gives a long-running Claude subprocess broad local machine authority without per-tool confirmation.
Install only if you intentionally want Claude Code to act as an unattended local agent through OpenClaw. Review the default disallowedTools setting before use, because the default permits shell commands and file edits under your user account, and use a dedicated workspace/account if you need containment.
SkillSpector was not run because this plugin release contains no bundled skills.
62/62 vendors flagged this plugin as clean.
Detected: suspicious.dangerous_exec, suspicious.exposed_secret_literal
log.info(`env for claude spawn (${Object.keys(cleanEnv).length} vars, names only): ${envKeys}`);var OAUTH_PLACEHOLDER_API_KEY = "[REDACTED]";