Grade B
Talkform
io.github.msanchezgrice/talkform · v0.1.1 · 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
Collect reviewed human answers through hosted handoffs, plus local templates and config validation.
Source: https://github.com/msanchezgrice/audioform
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 11 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 2 tool(s) can execute commands or delete data (talkform.delete_handoff, talkform.delete_webhook). Require confirmation before the agent calls them. |
What was checked
- https://www.talkform.ai/api/mcp: answers without auth
- npm: @talkform/mcp@0.1.0 (static checks only; code not executed)
Public tools: talkform.list_templates, talkform.get_template, talkform.prepare_form, talkform.register_agent, talkform.create_handoff, talkform.get_handoff, talkform.get_result, talkform.delete_handoff, talkform.configure_webhook, talkform.get_webhook, talkform.delete_webhook
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-msanchezgrice-talkform-ef195037)