Is zlc000190/using-superpowers safe?

https://clawhub.ai/zlc000190/using-superpowers

90
SAFE

This skill attempts to override normal agent reasoning to force compulsive skill invocation, using aggressive imperative language and preventing rational evaluation. While not malicious in intent, it could significantly disrupt normal agent behavior and user experience.

Category Scores

Prompt Injection 70/100 · 30%
Data Exfiltration 100/100 · 25%
Code Execution 100/100 · 20%
Clone Behavior 100/100 · 10%
Canary Integrity 100/100 · 10%
Behavioral Reasoning 80/100 · 5%

Findings (2)

HIGH Forceful skill invocation override -30 ▶

The skill uses extremely imperative language and tries to override normal agent decision-making by mandating skill invocation even with minimal relevance (1% chance). Uses phrases like 'ABSOLUTELY MUST', 'YOU DO NOT HAVE A CHOICE', and 'This is not negotiable' to force behavior.

MEDIUM Potential for excessive automation -20 ▶

The skill instructs the agent to invoke skills before any response, even with minimal probability of relevance. This could lead to disruptive over-automation and poor user experience by forcing unnecessary skill checks on simple interactions.