Is machinesbefree/moltbook-firewall safe?

https://github.com/openclaw/skills/tree/main/skills/machinesbefree/moltbook-firewall

95
SAFE

This is a well-designed defensive security skill that protects AI agents from prompt injection, social engineering, and malicious content on social platforms. The skill operates entirely locally, performs content scanning using safe pattern matching techniques, and shows no signs of malicious behavior during installation or operation.

Category Scores

Prompt Injection 98/100 · 30%
Data Exfiltration 98/100 · 25%
Code Execution 90/100 · 20%
Clone Behavior 100/100 · 10%
Canary Integrity 100/100 · 10%
Behavioral Reasoning 90/100 · 5%

Findings (2)

LOW Executable shell script present -10

The skill includes a shell script for content scanning functionality. While the script appears safe and serves the stated security purpose, any executable code represents a minor risk.

INFO Threat pattern disclosure -2

The skill openly documents threat detection patterns, which could theoretically help attackers understand what to avoid. However, this is standard practice for security tools and the defensive value outweighs this concern.