Whisper
io.github.whisper-sec/whisper · v0.273.0 · 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
One routable IPv6 per AI agent, verifiable from the DNS root. Keyless tools need no signup.
Source: https://github.com/whisper-sec/whisper-cli
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 42 tool(s) to anyone, no credentials needed. |
| Medium | MW002 | Package ghcr.io/whisper-sec/whisper:0.273.0 is published without a fixed version. |
What was checked
- https://whisper.online/mcp: answers without auth
- npm: @whisper-security/whisper-mcp@0.273.0 (static checks only; code not executed)
- oci: ghcr.io/whisper-sec/whisper:0.273.0@? (static checks only; code not executed)
Public tools: whisper_signup, whisper_verify, whisper_rdap, whisper_identify, whisper_assess, whisper_walk, whisper_watch, whisper_submit, whisper_explain, whisper_variants, whisper_origins, whisper_history, whisper_lookupTlsFingerprint, whisper_lookupTorRelay, whisper_asset, whisper_threatintel, whisper_psl, whisper_topAsnsByPrefixCount, whisper_agents_agent, whisper_agents_alert, whisper_agents_connect, whisper_agents_detect, whisper_agents_disconnect, whisper_agents_domain, whisper_agents_edge, whisper_agents_firewall, whisper_agents_history, whisper_agents_host, whisper_agents_identity, whisper_agents_list
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-whisper-sec-whisper-6f2af4e8)