Message Injector

OpenClaw plugin that prepends custom text to every user message before it reaches the agent. Use for: enforcing memory_search before replies, injecting syste...

This skill appears internally consistent with its purpose. Before installing: (1) Understand it will prepend configured text to every user message at the gateway level and agents cannot ignore it — this can change behavior across all users and channels in the workspace. (2) Back up ~/.openclaw/openclaw.json before editing so you can revert. (3) Keep prependText free of secrets or personally identifying data (it will be sent with every message). (4) Installation is manual: the provided code is short and readable; review the included scripts/index.ts yourself (it simply returns prependContext when configured). (5) If you share this workspace, coordinate with other users because the injection is global. If you want scoped or temporary injection, consider toggling enabled or using a different mechanism that targets specific agents or channels.

Type: OpenClaw Skill Name: message-injector Version: 1.0.0 The OpenClaw Message Injector plugin is designed to prepend custom text to every user message before it reaches the AI agent. This functionality, while powerful and effectively a form of persistent prompt injection, is the plugin's stated purpose and is implemented without any malicious code or instructions. The `SKILL.md` documentation clearly explains this mechanism and provides examples for legitimate use cases such as enforcing memory search, adding context, or injecting safety rules. The `scripts/index.ts` code simply retrieves the user-configured `prependText` and returns it via the `prependContext` hook, without any file system operations, network calls, or attempts at data exfiltration, persistence, or unauthorized execution. The plugin itself is a neutral tool; its potential for misuse depends entirely on the text configured by the user, not on any inherent maliciousness in the plugin's design or implementation.