Oathe Security Badge

Is millibus/smart-model-switching safe?

https://github.com/openclaw/skills/tree/main/skills/millibus/smart-model-switching

98
SAFE

This skill provides legitimate guidance for optimizing Claude API costs through intelligent model selection (Haiku → Sonnet → Opus). It contains educational content about cost-effective model usage with no malicious code, data exfiltration attempts, or security risks detected.

Category Scores

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

Findings (2)

LOW Complex model selection instructions -5

The skill contains detailed instructions for model selection that could theoretically be misinterpreted, but no actual prompt injection attempts are present.

INFO Cost optimization could benefit bad actors -5

The skill provides legitimate cost optimization guidance that could theoretically help malicious actors reduce their API costs, but this is a normal and expected use case.