Skills/Glama/claude-voice-mcp

claude-voice-mcp@1.0.0

VERIFIED· install only

Publisher claims: "Enables the Claude mobile app's voice mode to send spoken requests to Claude Code running headless on a Mac and receive concise, read-aloud answers, while preserving access to the Mac's files, CLIs, notes, and other tools through a secure remote MCP connection." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher guillaume-gonano · publishing for 2 daysInstalls 0Last detonated 39 h ago
$npx skills add claude-voice-mcp
WatchReport an issue

Coverage

Install scripts ran; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
MIN_PASSWORD_LENGTHNEW_PASSWORDConfiguration, not credentials: CLAUDE_BIN, FAKE_SLEEP, VOICE_MCP_EFFORT, VOICE_MCP_MAX_RUNNING, VOICE_MCP_MODEL, VOICE_MCP_WAIT_MS
Where it talks to
no vendor host named in the codeAlso claude.ai, apple.com, claude.com, evil.example — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names claude.ai, apple.com, claude.com, evil.example as well as its own vendor. The guard injects MIN_PASSWORD_LENGTH, NEW_PASSWORD only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- <the server's command>

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-12 and scored it 91/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessexec /usr/bin/dirname
0.0sprocessexited 1:
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocesssecond launch, clock +45 days, CI unset
0.1sprocessexec /usr/bin/dirname
0.1sprocessexited 1:

Static findings

MEDIUM
File permission modification commandscripts/install.sh:88 · File permission modification command — agent changes file ownership/permissionschmod 644 "$LA/$1.plist"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

No other findings across 2,121 lines in 11 files.

Cost to the agent

Instructions loaded
≈325 tok
2 files · 11 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.