Security audit
Security checks for vulnerabilities and agentic risk
This book-tracking skill stores local reading preferences and book lists for its stated purpose, with no evidence of hidden execution, exfiltration, or unrelated authority.
Install if you are comfortable with a local reading tracker that records your books, wishlist, moods, ratings, and taste notes over time. Review or delete books/ and memory/library.md if you do not want that history retained.
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
## Taste Profile
<!-- What kind of reader are you? Fill in as you learn. -->
- Fiction: ___%, Non-fiction: ___%
- Preferred genres: ___
- Avoids: ___
The description says to use the skill when the user asks about books, reading recommendations, what to read next, or updating a reading tracker, and initialization begins when 'ANY book-related trigger fires.' This is broader than the explicit trigger list and could cause unintended invocation on ordinary conversation about books without clear boundaries or exclusion conditions.
The skill persistently stores reading history, taste profile, mood map, and preference notes in local files without clearly warning the user that this data will be retained over time. That creates a privacy risk because sensitive inference data about interests, emotions, habits, and opinions can accumulate silently and be reused beyond the immediate request.
No suspicious patterns detected.