Is hw10181913/claude-code safe?

https://github.com/openclaw/skills/tree/main/skills/hw10181913/claude-code

97
SAFE

This skill provides a safe wrapper for Claude Code documentation and basic task management functionality. The code is straightforward, serves only hardcoded documentation content, and shows no signs of malicious behavior during installation or execution. All security monitoring indicates normal, expected behavior with no attempts at data exfiltration or system compromise.

Category Scores

Prompt Injection 95/100 · 30%
Data Exfiltration 100/100 · 25%
Code Execution 95/100 · 20%
Clone Behavior 100/100 · 10%
Canary Integrity 100/100 · 10%
Behavioral Reasoning 95/100 · 5%

Findings (2)

LOW Executable Python script included -5

The skill includes a Python script (claude-code.py) that will be executed when the skill is used. However, analysis shows it only serves hardcoded documentation content without external network calls or file system access.

INFO Third-party skill content -5

As a third-party skill, the content should be reviewed for accuracy, though no malicious prompt injection patterns were detected in the SKILL.md content.