← Back to Skills Marketplace
Test Safety
by
John-niu-07
· GitHub ↗
· v1.0.2
· MIT-0
248
Downloads
1
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install safety-guard-skill-xidian
Description
Security guard skill for OpenClaw - Analyzes user input for harmful content, risky commands, and security threats before invoking LLM
Usage Guidance
Do not install or provide API keys yet. Steps to take before trusting this skill: 1) Inspect the referenced GitHub repo and confirm the CLI or Python code actually exists and matches this SKILL.md. 2) Verify author/owner identity (the registry metadata and _meta.json disagree on slug/owner/version). 3) If you plan to use it, run it in a sandboxed environment (no real API keys) and monitor network calls to see what endpoints it contacts. 4) Confirm what files it will read/write (it mentions ~/.safety-guard/config.json) and that it won’t exfiltrate sensitive data. 5) Prefer least-privilege API keys (scoped, revocable) and rotate them after testing. If you can't find source code that implements the CLI behavior described, treat the skill as incomplete/untrustworthy.
Capability Analysis
Type: OpenClaw Skill
Name: safety-guard-skill-xidian
Version: 1.0.2
The skill bundle contains metadata and documentation for a 'Safety Guard' tool designed to analyze user input for security threats. The files (_meta.json and SKILL.md) describe standard functionality, including dependency installation (PyYAML) and the use of environment variables for LLM API keys. While the documentation references non-existent future models (e.g., GPT-5.2, Gemini-3) and includes a Rickroll URL (dQw4w9WgXcQ) in its examples, there is no evidence of malicious code, data exfiltration, or prompt injection attacks within the provided content.
Capability Assessment
Purpose & Capability
The skill claims to analyze input for harmful content and references LLM provider API keys (OpenAI, Anthropic, xAI, Google). Those requirements are proportionate to a safety-guard skill. However, the skill is instruction-only (no code provided) yet shows CLI usage examples for a 'safety-guard' binary that is not included — unclear how runtime behavior is supplied, which reduces confidence in capability claims.
Instruction Scope
SKILL.md describes fetching content from URLs, local files, and YouTube and references optional external services (FIRECRAWL, APIFY). Those actions are plausible for content-extraction and safety checks, but the file also references a user config path (~/.safety-guard/config.json) that isn't declared in the registry metadata. Because the skill can instruct fetching external resources and reading/writing a local config, you should verify exactly what code will run and what data will be read or transmitted before use.
Install Mechanism
Registry metadata at the top-level reported 'No install spec', yet SKILL.md includes embedded metadata that lists a pip install step for PyYAML and requires python3. Additionally, the included _meta.json file does not match the registry metadata (different slug/owner/version). These inconsistencies suggest packaging or provenance problems — either the skill is incomplete (instruction-only but references an external CLI not supplied) or files were copied/mislabelled. That mismatch increases risk because you can't verify what will be installed/run.
Credentials
The skill does not declare any required environment variables and only suggests standard LLM provider API keys and optional API tokens for content-extraction services. Those are proportionate for a safety-guard that needs to call LLMs and optional crawlers. No unrelated credentials (cloud keys, SSH keys, etc.) are requested.
Persistence & Privilege
The skill is not always-enabled, is user-invocable, and does not request persistent privileges in the metadata. It mentions an optional local config path (~/.safety-guard/config.json) which would be typical for a CLI tool, but the presence of that path in SKILL.md without being declared is a packaging inconsistency to verify.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install safety-guard-skill-xidian - After installation, invoke the skill by name or use
/safety-guard-skill-xidian - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
- Improved documentation and usage instructions in SKILL.md
- Added details about supported models, API keys, and configuration options
- Clarified optional flags and fallback services for enhanced usability and flexibility
Metadata
Frequently Asked Questions
What is Test Safety?
Security guard skill for OpenClaw - Analyzes user input for harmful content, risky commands, and security threats before invoking LLM. It is an AI Agent Skill for Claude Code / OpenClaw, with 248 downloads so far.
How do I install Test Safety?
Run "/install safety-guard-skill-xidian" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Test Safety free?
Yes, Test Safety is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Test Safety support?
Test Safety is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Test Safety?
It is built and maintained by John-niu-07 (@john-niu-07); the current version is v1.0.2.
More Skills