Skills/npm/granttap-mcp

granttap-mcp@0.8.157

CAUTION· not started

Publisher claims: "Commercial computer runtime connecting local coding agents to GrantTap on Mac, iPhone, iPad and Apple Watch." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher sergii-ziborov · publishing for 113 daysInstalls 19,121Last detonated 8d ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution 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

Code inventory arrives with this version's next honeypot run.
It will ask for
unknown until the next run
Where it talks to
unknown until the next run
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Not enough was observed to say yet. Not started: dependency install failed; the server itself was not observed. This version's code has not been inventoried for credentials and hosts either; both arrive with its next honeypot run (popular servers first). `vet-skills try granttap-mcp` runs it now and prints the full answer.

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; not started: dependency install failed; the server itself was not observed) on 2026-11-07 and scored it 71/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Pipe-to-shell pattern; Auto-update or dynamic fetch configuration. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.8sprocessdependency install exit 1
0.8sprocessexec /usr/bin/date
0.8sprocessexec /usr/bin/timeout
0.8sclaimedno tools/list reply (exit 0)
0.8sprocessscript backend runs setup only
0.8sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagecursor-plugin/stdio-bootstrap.cjs:25 · npx invocation of non-well-known package — may execute untrusted codeconst npx = first(roots.map((root) => join(root, "npx"))) || "npx";Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsapps/bridge/src/tools/updater.ts:264 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst updaterEnv = { ...env, PATH: [nodeDirectory, env.PATH ?? ''].join(delimiter) };Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)apps/mcp/src/bin/serve.ts:1 · MCP server using network transport (SSE/HTTP) — data sent over networkimport { startHttpMcpServer } from "../http/http-server";Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
CRITICAL
Pipe-to-shell patternapps/bridge/src/tools/updater.ts:192 · Pipe-to-shell pattern — downloads and immediately executes remote code+ "In a trusted terminal: curl -fsSL https://chatgpt.com/codex/install.sh | sh";Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Auto-update or dynamic fetch configurationbin/granttap-mcp.mjs:22 · Auto-update or dynamic fetch configuration — agent may load new code at runtime&& process.env.GRANTTAP_DISABLE_AUTO_UPDATE !== "1" && !process.env.NODE_TEST_CONTEXT;Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsapps/bridge/src/tools/updater.ts:210 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filescwd, env: { ...env, NO_COLOR: "1", CI: "1" }, stdio: ["ignore", "pipe", "pipe"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shellapps/bridge/src/tools/updater.ts:192 · Remote installer piped to shell+ "In a trusted terminal: curl -fsSL https://chatgpt.com/codex/install.sh | sh";Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
npx invocation of non-well-known packagecursor-plugin/mcp.json:7 · npx invocation of non-well-known package — may execute untrusted code"\"use strict\";\n\n// Cursor may start this MCP from any cwd. Execute JavaScript entry points with\n// Node itself: Windows batch shims require shell quoting that differs by host.\nconst { spawn } = Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagecursor-plugin/stdio-bootstrap.cjs:31 · npx invocation of non-well-known package — may execute untrusted codeconst npx = first(roots.map((root) =>Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈64 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for granttap-mcp@0.8.157 as of 8d ago. This is the package itself, not its dependencies.

What would make this Verified

9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Unclaimed publisher≈ +8 on the totalClaim sergii-ziborov: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  6. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim sergii-ziborovPropose a patch to the maintainer