Skills/ClawHub/apple-swift-mcp

apple-swift-mcp@2.11.0

VERIFIED· install only

Publisher claims: "This skill should be used when the user asks about Apple app data via the native Swift MCP — Calendar, Reminders, Contacts, Maps, Mail, Messages, Notes, Photos, or Apple Music playlists on macOS. Triggers on phrases like "check my calendar", "find contact", "send iMessage", "search my notes", "recent emails", "find photos of", "make a playlist", "add this song to my playlist", "sort my playlist", or any macOS-native app automation. Requires macOS 27.2+ on Apple Silicon; faster than the AppleScript-backed Node variant." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher chrischall · publishing for 216 daysInstalls 2,847Last detonated 5d ago
$clawhub install apple-swift-mcp
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-09 and scored it 92/100 (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 · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actionSKILL.md:138 · File type combined with upload action — agent may exfiltrate local data files…eview lists everyone in it; omit `service`). The answer is checked against `chat.db` for up to ~5 seconds: it names the service the message actually went out on (including an SMS fallback from iMessage, or Messages downgrading it), and say…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:137 · File type combined with upload action — agent may exfiltrate local data files…o list only chats with unread messages — refused, not answered empty, when `chat.db` records no read state), `chat` (one chat's name, identifier, GUID, service and participants; `chatID`), `read` (history from `chat.db`, newest first; `cha…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionSKILL.md:235 · File type combined with upload action — agent may exfiltrate local data files- `messages_read` reads `chat.db` directly for history; `messages_send` uses AppleScript.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈4,771 tok
1 file · 1 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.