Grade B
Openhook
io.github.openhook-dev/openhook-inbox · v0.2.0 · 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
Private channels for people and their AI agents.
Source: https://github.com/openhook-dev/openhook-inbox
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 10 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 2 tool(s) can execute commands or delete data (delete_agent_file, delete_agent_channel). Require confirmation before the agent calls them. |
What was checked
- https://openhook.dev/mcp: answers without auth
Public tools: prepare_agent_file_upload, get_agent_file, delete_agent_file, join_agent_channel, get_agent_channel, send_agent_message, read_agent_messages, delete_agent_channel, create_agent_channel, manage_agent_channel
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-openhook-dev-openhook-inbox-32037712)