secure-applemusic-mcp-for-osx@0.3.1
VERIFIED· install onlyPublisher claims: "Control Apple Music on macOS with Claude: play, search, build playlists, add music to your library. No account, no API key, nothing stored." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 18 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · 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
APPLEMUSIC_FORCE_TOKENLESSAPPLEMUSIC_USER_TOKENConfiguration, not credentials: APPLEMUSIC_APP_BUNDLE, APPLEMUSIC_CACHE_DIR, APPLEMUSIC_CONFIG_DIR, APPLEMUSIC_DATA_DIR, APPLEMUSIC_FORCE_API_MODE, APPLEMUSIC_MCP_HOME- Where it talks to
- no vendor host named in the codeAlso apple.com — 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 apple.com as well as its own vendor. The guard injects APPLEMUSIC_FORCE_TOKENLESS, APPLEMUSIC_USER_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.
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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 81/100 (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 · 1 s · 2 scenarios · 0 deviationsStatic findings
# (Apple Events -> document.cookie) or by driving a Playwright Chrome.Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(["launchctl", *args], capture_output=True, text=True, timeout=60)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.res = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# write. Gating on "is the binary on disk" honoured neither that killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.except Exception as exc: # noqa: BLE001 - a session must not kill the helperFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# write. Gating on "is the binary on disk" honoured neither that killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- Scripts are executed via subprocess.run() with capture_output=TrueFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# change exists to kill (#42), so they stay separate.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# write. Gating on "is the binary on disk" honoured neither that killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.proc = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# in their `env` blocks — a write-then-chmod leaves those world-readable forFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.except Exception as exc: # noqa: BLE001 - a step must not kill the wizardFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.quarantine = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# directory we don't own (/tmp). Failing to chmod someone else's directoryFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run([str(exe), *args], capture_output=True, text=True, timeout=_TIMEOUT)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
No advisories in OSV for secure-applemusic-mcp-for-osx@0.3.1 as of 7 min ago. This is the package itself, not its dependencies.