Missing User Warnings
Medium
- Confidence
- 96% confidence
- Finding
- The skill indexes and answers questions by reading local files and sending extracted content, summaries, and possibly full document text to the LLM, but the description does not warn users about that data flow. This creates a privacy and consent problem: users may reasonably believe the tool is purely local when in fact sensitive document contents can be exposed to the model during indexing and Q&A.
