Grade B
hedwigai
com.hedwigai/hedwigai · v1.4.0 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
The system of record for your agent: workbooks it reads and writes, with sources, kept current.
Source: https://github.com/un-seen/hedwigai-skills
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 21 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 2 tool(s) can execute commands or delete data (delete_workbook, bash). Require confirmation before the agent calls them. |
What was checked
- https://mcp.hedwigai.com: answers without auth
- npm: hedwigai@1.0.1 (static checks only; code not executed)
Public tools: find_workbooks, read_workbook, create_workbook, write_workbook, run_workbook, workbook_runs, configure_workbook, link_workbook, checkout_workbook, share_workbook, attachments, upload, folders, edit_folders, mirror_workbook, ask, delete_workbook, restore_workbook, bash, credits, render_document
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/com-hedwigai-hedwigai-bae6fa6b)