- name
- ClawShield Lite
- description
- Scans AI skills for potential security risks and unsafe commands
- version
- 0.1
- input
- code (string)
- output
- report (JSON string)
- run
- python main.py
ClawShield Lite
A lightweight security analysis skill that scans AI skill code for risky patterns and outputs a structured risk report.
How It Works
- Accepts code input via
stdin(string or file content) - Loads pattern definitions from
rules.json - Scans the input for dangerous and suspicious patterns
- Assigns a risk level:
SAFE,MEDIUM RISK, orHIGH RISK - Outputs a JSON report with all findings
Usage
echo "import os; os.system('rm -rf /')" | python main.py