Back to skill
Skillv1.0.1

ClawScan security

Library Book Monitor · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignMar 6, 2026, 4:17 AM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill's code, instructions, and permissions are consistent with a library availability monitor; there are no obvious mismatches or hidden endpoints.
Guidance
This skill appears to do exactly what it says: it scrapes the Shenzhen Library API, stores tracked books in book_list.json, and can notify via console or SMTP email. Before installing or running: 1) Review config.yaml (it will contain any SMTP password you provide) and consider using an app-specific or throwaway SMTP account if you’re concerned; 2) Inspect the included Python files (they are provided) and only run pip install -r requirements.txt from a trusted environment; 3) Be aware that 'python main.py monitor' starts a persistent process that will periodically query the library (set reasonable interval to avoid heavy requests); 4) If you require provenance, verify the package source (package.json references a GitHub repo) — the skill metadata at the top said source/homepage unknown, so prefer installing from the upstream repository or review the repo before use.

Review Dimensions

Purpose & Capability
okName/description (monitor library book availability for Shenzhen Library) aligns with requested permissions (network/filesystem/shell) and included code (scraper, scheduler, notifier, book storage). There are no unrelated credentials or services requested.
Instruction Scope
okSKILL.md instructs the agent to run the packaged Python CLI (main.py add/list/check/remove/toggle/monitor) and to use a local config.yaml and book_list.json. The instructions do not ask the agent to read unrelated system files, nor to exfiltrate data to unknown endpoints; network calls go to the Shenzhen library API endpoints implemented in the scraper.
Install Mechanism
noteThere is no install spec (instruction-only install), but the package includes Python source and a requirements.txt. SKILL.md instructs users to run pip install -r requirements.txt manually. This is low risk, but the skill will execute local Python code when invoked, so users should review source before running.
Credentials
okThe skill declares no required environment variables. Notification via email requires SMTP credentials, but those are stored in config.yaml (local file) rather than environment variables; this is proportionate to the stated notification feature. requirements.txt includes python-dotenv though the code does not use it—minor inconsistency.
Persistence & Privilege
notealways:false and the skill does not modify other skills or system-wide configs. However, running the 'monitor' command starts a long-running scheduler loop that performs periodic network requests and writes to book_list.json; if invoked by the agent it will spawn a persistent process until stopped.