Voice-first Mac assistant that uses the computer for you. GPT-Live-1 voice, vendor-neutral brains (Codex, Claude Code, any API), native Swift hands, an ASCII blob that shows its work.
- capability exposure inferred + 35
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.
grade last moved 19h ago · see ecosystem CVEs →
- A · 0 → C · 35
No known CVEs for this server.
- low dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
analyzed commit f6c3b40 · analyzer v33 · 4h ago
skills & prompt files 1
- agent-rules Kevin-Liu-01-Jarhead-f6c3b40/AGENTS.md
danger signals3
- suspicious endpoint 169.254.169.254 (cloud metadata) Kevin-Liu-01-Jarhead-f6c3b40/packages/core/src/__tests__/policy.test.ts :524
assert.equal(v("http://169.254.169.254/latest/meta-data/", "read https://example.com"), "refuse", "link-local is private"); - over-broad OAuth scope https://mail.google.com/ Kevin-Liu-01-Jarhead-f6c3b40/packages/brain/src/reflex.ts :181
gmail: "https://mail.google.com/", - over-broad OAuth scope https://mail.google.com/ Kevin-Liu-01-Jarhead-f6c3b40/packages/core/src/__tests__/policy.test.ts :579
assert.ok(presenceGated(undefined, "https://mail.google.com/mail/u/0/#inbox"));
[](https://mcpobservatory.com/servers/github:Kevin-Liu-01/Jarhead/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 Kevin-Liu-01.