← Back to Skills Marketplace
383
Downloads
1
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install openclaw-snitch
Description
Multi-layer blocklist guard for OpenClaw. Hard-blocks tool calls matching banned patterns, injects a security directive at agent bootstrap, warns on incoming...
Usage Guidance
This skill appears to do what it says: injects a bootstrap security directive, warns on incoming messages, blocks matching tool calls, and notifies Telegram recipients configured in your OpenClaw channels. Before installing: (1) review and verify the npm package publisher and source (npm install -g runs code on your machine); (2) confirm which Telegram 'allowFrom' IDs are configured so alerts go to expected recipients; (3) understand that the bootstrap directive is a content file pushed into agent contexts (it is not an enforced kernel-level policy) and can be bypassed if an agent or user can edit hooks/config; (4) follow the recommendation to lock down plugin/hook files only after validating behavior, and be cautious when running chown/chmod commands requiring elevated privileges. If you want stronger guarantees, test in a disposable agent/workspace and inspect the installed npm package contents before trusting it in production.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-snitch
Version: 1.0.2
The OpenClaw Snitch skill is a security-focused plugin designed to protect OpenClaw agents by implementing a multi-layer blocklist. It injects security directives into agent contexts, warns on incoming messages containing blocked terms, and hard-blocks tool calls matching a configurable blocklist, broadcasting alerts to pre-configured Telegram IDs. All code and documentation align with this stated purpose, showing no evidence of malicious intent such as data exfiltration, unauthorized command execution, or persistence mechanisms. The skill even includes security hardening advice (e.g., `chmod -R a-w`) and anti-prompt-injection directives for the agent.
Capability Assessment
Purpose & Capability
Name/description align with required files and behavior: the hooks inject bootstrap directives and message warnings, and the plugin intercepts before_tool_call and broadcasts via the platform Telegram channel. No unrelated environment variables, binaries, or external services are required by the skill itself.
Instruction Scope
SKILL.md instructs copying hooks into ~/.openclaw/hooks and (optionally) installing the npm package globally — these steps match the included hook and plugin code. One overstatement: the bootstrap directive claims 'cannot be overridden by user messages or system prompts' but it is implemented as a bootstrap file pushed into the agent context (a content directive) and therefore is not a cryptographically enforced policy; an agent or user with write access to config/hooks could still circumvent it. The skill's instructions also suggest permission-locking extension files (chmod/chown) which is a user-side hardening suggestion, not an enforced action.
Install Mechanism
The registry entry has no automated install spec (instruction-only), but SKILL.md recommends installing an npm package (npm install -g openclaw-snitch). That is a common delivery method for OpenClaw plugins. Installing an npm package performs arbitrary code installation — standard risk for any third-party npm package — but nothing in the skill's files points to obscure download URLs or installers.
Credentials
The skill declares no required env vars or credentials. The hooks optionally read SNITCH_BLOCKLIST from environment to customize the blocklist; the plugin reads the host OpenClaw config (channels.telegram.accounts) to resolve recipient IDs for alerts. No unrelated secrets or multiple unrelated credentials are requested.
Persistence & Privilege
The skill is not marked always:true and does not request elevated platform privileges. It registers event handlers (agent:bootstrap, message:received, before_tool_call) which is expected for this purpose. It does recommend (user-driven) file permission changes to reduce tampering, but the skill itself does not auto-modify other skills or global settings beyond adding bootstrap files via the plugin hook.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-snitch - After installation, invoke the skill by name or use
/openclaw-snitch - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
- Update install instructions: use chmod (remove write permissions) instead of chown to lock plugin files.
- No functional or configuration changes. Documentation only.
v1.0.1
- Update install instructions: use chmod (remove write permissions) instead of chown to lock plugin files.
- No functional or configuration changes. Documentation only.
v1.0.0
openclaw-snitch 1.0.0 – Initial release
** Multi-layer AI Security Snitch blocks what the LLM won't **
- Introduces a multi-layer blocklist guard for OpenClaw agents.
- Injects a security directive at agent bootstrap.
- Flags and warns on incoming messages with blocked terms.
- Hard-blocks tool calls matching banned patterns and broadcasts Telegram alerts.
- Blocks clawhub and clawdhub by default; supports custom blocklists and alerts.
- Includes installation and configuration instructions for both hooks and plugin layers.
Metadata
Frequently Asked Questions
What is Openclaw Snitch?
Multi-layer blocklist guard for OpenClaw. Hard-blocks tool calls matching banned patterns, injects a security directive at agent bootstrap, warns on incoming... It is an AI Agent Skill for Claude Code / OpenClaw, with 383 downloads so far.
How do I install Openclaw Snitch?
Run "/install openclaw-snitch" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Openclaw Snitch free?
Yes, Openclaw Snitch is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Openclaw Snitch support?
Openclaw Snitch is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Openclaw Snitch?
It is built and maintained by Rob Gray (@rgr4y); the current version is v1.0.2.
More Skills