Is manikantasai1987/manikantasai-playwright-automation safe?

https://github.com/openclaw/skills/tree/main/skills/manikantasai1987/manikantasai-playwright-automation

92
SAFE

This skill provides comprehensive documentation and examples for Playwright browser automation without containing malicious code or exhibiting dangerous installation behavior. While it includes executable Python examples and browser automation knowledge that could theoretically be misused, the content is legitimate educational material.

Category Scores

Prompt Injection 95/100 · 30%
Data Exfiltration 90/100 · 25%
Code Execution 85/100 · 20%
Clone Behavior 95/100 · 10%
Canary Integrity 100/100 · 10%
Behavioral Reasoning 80/100 · 5%

Findings (3)

LOW Contains executable Python example script -15 ▶

The skill includes a Python file (examples.py) with executable code that demonstrates Playwright MCP tool usage. While the code is benign and only prints example outputs rather than executing actual browser automation, it represents executable content within the skill.

LOW Sensitive file access during installation -10 ▶

Monitoring detected access to sensitive canary files (.env, SSH keys, AWS credentials) during installation. However, analysis suggests this was part of the security monitoring system testing rather than malicious behavior by the skill.

INFO Browser automation knowledge could enable misuse -20 ▶

The skill provides comprehensive documentation about browser automation capabilities using Playwright. While educational and legitimate, this knowledge could potentially be misused for unauthorized web scraping, circumventing rate limits, or accessing websites in unintended ways.