Skill flagged suspicious: https://clawhub.ai/jlevitsk/prepper #143

Open
opened 2026-02-15 17:15:54 -05:00 by yindo · 0 comments
Owner

Originally created by @jlevitsk on GitHub (Feb 12, 2026).

So my skill was flagged as suspicious https://clawhub.ai/jlevitsk/prepper and in a way I understand why it would do that if it looks lightly at the skill. The skill is meant for prepper / disaster planning to use a ollama model that has info on preparedness and what it tries to do is get info both from the commercial model you might be using as your actual model -and- the ollama model and then provide a hybrid answer. In some cases if the commercial model won't give any info on a topic then the ollama model is the only source. So I can see how it might see that as deceptive but on the other hand maybe there's an opportinity for me to either document the skill in a better way or for the malware detection to be improved.

Originally created by @jlevitsk on GitHub (Feb 12, 2026). So my skill was flagged as suspicious https://clawhub.ai/jlevitsk/prepper and in a way I understand why it would do that if it looks lightly at the skill. The skill is meant for prepper / disaster planning to use a ollama model that has info on preparedness and what it tries to do is get info both from the commercial model you might be using as your actual model -and- the ollama model and then provide a hybrid answer. In some cases if the commercial model won't give any info on a topic then the ollama model is the only source. So I can see how it might see that as deceptive but on the other hand maybe there's an opportinity for me to either document the skill in a better way or for the malware detection to be improved.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: openclaw/clawhub#143