Agent gateway for external tools — Rhumb Index scores services; Rhumb Resolve routes supported capability calls through governed execution rails.
- capability exposureinferred+35
- recent driftinferred+12
- tool safetyinferred+25
inferred
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 2m ago · see ecosystem CVEs →
- C · 59 → D · 72
- D · 71 → C · 59
No known CVEs for this server.
- highexfiltration combocredential_ceremony
single tool reads + sends: net, secrets
- mediumpurpose mismatchresolve_capability
benign-looking name carries shell, secrets
- mediumpurpose mismatchestimate_capability
benign-looking name carries shell
- mediumpurpose mismatchrhumb_recipe_execute
benign-looking name carries shell
- mediumpurpose mismatchrouting
benign-looking name carries shell
analyzed commit d1dbd8d · analyzer v20 · 1d ago
danger signals4
- over-broad OAuth scopehttps://www.googleapis.com/auth/cloud-platformsupertrained-rhumb-d1dbd8d/packages/api/services/bigquery_read_executor.py:115
"https://www.googleapis.com/auth/cloud-platform", - over-broad OAuth scopehttps://www.googleapis.com/auth/cloud-platformsupertrained-rhumb-d1dbd8d/scripts/mint_google_authorized_user_adc.py:42
"https://www.googleapis.com/auth/cloud-platform", - over-broad OAuth scopesite_adminsupertrained-rhumb-d1dbd8d/scripts/runtime_review_github_depth10_20260402.py:36
"site_admin", - over-broad OAuth scopesite_adminsupertrained-rhumb-d1dbd8d/scripts/runtime_review_github_depth4_20260401.py:173
for field in ["login", "id", "type", "site_admin", "name", "company", "blog", "location", "public_repos", "created_at"]:
- recent drift+12 capability drift →
[](https://mcpobservatory.com/servers/github:supertrained/rhumb/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of supertrained.