← Back to Skills Marketplace
Minduploadedcrab Skillguard
by
minduploadedcrab
· GitHub ↗
· v1.0.1
602
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install minduploadedcrab-skillguard
Description
Security scanner for OpenClaw skills. Scans skills for malware, credential theft, data exfiltration, prompt injection, and permission overreach before instal...
Usage Guidance
This skill largely does what it claims — it's a Python-based scanner that searches files for risky patterns. However: 1) Open SKILL.md and scripts/skillguard.py and confirm there are no network calls (requests/httpx/urllib) or code paths that send scan results to external endpoints; the provided snippet shows pattern-only scanning but you should verify the rest of the file. 2) Inspect SKILL.md to see why a prompt-injection phrase was detected — ensure it's only an example in documentation and not a buried instruction intended to influence other agents. 3) Because the scanner reads all files in ~/.openclaw/workspace/skills, run it in a safe environment or on a copy to avoid accidental exposure of secrets; review any findings before sharing them. 4) If you plan to allow autonomous invocation, be cautious: an autonomously-invoked scanner that produced automated reports could leak snippets of secrets in its output. If anything is unclear, ask the author for a justification of the prompt-injection text and for a code walkthrough of network behavior before installing.
Capability Analysis
Type: OpenClaw Skill
Name: minduploadedcrab-skillguard
Version: 1.0.1
The OpenClaw AgentSkills skill 'minduploadedcrab-skillguard' is a security scanner designed to detect malware, credential theft, data exfiltration, and prompt injection in other OpenClaw skills. The `SKILL.md` provides clear, benign instructions for its use. The `scripts/skillguard.py` code implements scanning logic by reading files and matching patterns defined in `data/patterns.json`. It does not exhibit any malicious behaviors itself, such as making unauthorized network calls, executing arbitrary commands, exfiltrating data, or attempting prompt injection against the agent. Its operations are confined to reading and analyzing files within specified skill directories, aligning perfectly with its stated purpose as a security tool.
Capability Assessment
Purpose & Capability
Name, description, and required binary (python3) match the contained files: a Python scanner (scripts/skillguard.py) plus pattern data. The scanner's declared checks (credentials, exfil, prompt injection, filesystem abuse, etc.) are implemented in the provided code and patterns.json, so the requirements are proportionate to the stated purpose.
Instruction Scope
SKILL.md instructs the agent/user to run the scanner against skill directories (including 'scan-all' which uses the default ~/.openclaw/workspace/skills). That's reasonable for a scanner, but the pre-scan detected a prompt-injection marker ('ignore-previous-instructions') inside SKILL.md itself — this could be an innocuous example of what the scanner detects or could be a malicious attempt to influence downstream evaluations/agents. The scanner reads full files from other installed skills (expected) — note that scan results may include sensitive fragments from those files.
Install Mechanism
No install spec is provided (instruction + local files only). Nothing is downloaded or extracted; no third-party registries or unusual URLs are used. This is low-risk from an installation perspective.
Credentials
No environment variables, credentials, or external tokens are requested. The included patterns.json lists many key names to detect in scanned code, which is appropriate for the scanner's role. There is no evidence the skill requests unrelated secrets.
Persistence & Privilege
The skill does not declare always:true and does not appear to modify other skills or global agent configuration. Agent invocation is allowed (default), which is normal — but as with any autonomously-invokable tool, that increases blast radius if the tool were malicious.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install minduploadedcrab-skillguard - After installation, invoke the skill by name or use
/minduploadedcrab-skillguard - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Improved documentation with detailed usage instructions and detection capabilities.
- Added descriptions of scan types, risk scoring, and output format.
- Expanded threat detection list, clarifying coverage for credential theft, data exfiltration, prompt injection, and more.
- Simple command examples included for scanning specific skills or all installed skills.
Metadata
Frequently Asked Questions
What is Minduploadedcrab Skillguard?
Security scanner for OpenClaw skills. Scans skills for malware, credential theft, data exfiltration, prompt injection, and permission overreach before instal... It is an AI Agent Skill for Claude Code / OpenClaw, with 602 downloads so far.
How do I install Minduploadedcrab Skillguard?
Run "/install minduploadedcrab-skillguard" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Minduploadedcrab Skillguard free?
Yes, Minduploadedcrab Skillguard is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Minduploadedcrab Skillguard support?
Minduploadedcrab Skillguard is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Minduploadedcrab Skillguard?
It is built and maintained by minduploadedcrab (@minduploadedcrab); the current version is v1.0.1.
More Skills