skills/edwinhu/workflows/readwise/Gen Agent Trust Hub

readwise

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/readwise_to_nlm.py executes a local binary located at /Users/vwh7mb/projects/nlm/nlm via subprocess.run to add content to NotebookLM. The operation uses a hardcoded absolute path and passes data through standard input.
  • [EXTERNAL_DOWNLOADS]: The skill performs network operations to readwise.io to fetch user library data, including full-text HTML content and highlights. These requests use the official API endpoints for the service.
  • [DATA_EXFILTRATION]: The scripts read a Readwise API token from a local file path (/var/folders/01/wzs3mqmn3jx2b81f0dcq9w8h0000gq/T/agenix/readwise-token) to authenticate API requests. This is consistent with the skill's primary purpose of managing a user's private Readwise library.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 02:35 AM