Safe command execution for AI agents with timeout control, 8KB ring buffer memory protection, background process management, and multi-agent sharing via HTTP...

This skill appears to implement exactly what it claims — a general-purpose command executor and background process manager — which inherently grants the ability to run arbitrary system commands and read their outputs. Before installing or enabling it, consider: 1) Network exposure: run the HTTP mode only bound to localhost or behind a firewall and add authentication; the skill's docs do not describe auth. 2) Principle of least privilege: run inside an isolated container or dedicated service account to limit file and credential access. 3) Environment leakage: child processes inherit process.env — do not run it on hosts holding sensitive environment variables unless you accept the risk. 4) Audit and limits: set strict max-process, timeouts, and logging retention; review code for any hidden telemetry or externally contacting behavior (package files are present but verify dependencies in package-lock.json). 5) Source trust: there's no homepage and the owner is unknown — prefer packages from known authors or verify signatures. If you need this capability but want lower risk, restrict HTTP mode, require authentication, or use CLI-only invocation in an isolated environment. Additional information that would raise confidence: a known upstream repository/homepage, published release on a reputable host, and a documented authentication or binding configuration for the HTTP server.

Type: OpenClaw Skill Name: exec-guard Version: 1.0.6 The skill bundle provides a powerful utility for arbitrary system command execution, featuring both a CLI and an unauthenticated Express-based HTTP server. While it includes legitimate safety features like timeout controls and a 'Head-Tail Ring Buffer' (in ringbuf.js) to prevent memory exhaustion from large outputs, the core functionality (executor.js and server.js) essentially provides a Remote Code Execution (RCE) interface. The ability to run background processes, set environment variables, and manage processes remotely via the /exec endpoint is a high-risk capability that could be easily exploited if the service is exposed or misused by an agent.