ClawHub
Back to skill

Security audit

Zoom Phone API MCP

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Zoom Phone MCP wrapper, but users should install the external binaries from trusted, controlled sources.

Before installing, verify the mcporter and zoom-phone-mcp binaries come from the intended publisher and version, run them with minimal environment access, and ensure Zoom API credentials are restricted to read-only scopes.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:4
Finding

Unpinned External MCP Executable Creates a Supply-Chain Trust Risk

Content
View full analysis
[args]` ## Links - **npm:** https://www.npmjs.com/package/@mjquinlan2000/zoom-phone-mcp ``` ### Technical Analysis The skill delegates its operational behavior to the external `mcporter` and `zoom-phone-mcp` executables. No exact package version, integrity hash, trusted installation path, lock file, or locally auditable implementation is included in the project. The executable is resolved by name from the runtime environment. Therefore, the behavior ultimately executed is determined by whichever binary named `zoom-phone-mcp` is installed and selected through executable path resolution. The manifest's claim that the server is read-only is descriptive rather than an enforceable security boundary; the repository contains no code or configuration that independently restricts the external process to read-only Zoom operations. The process also receives an environment containing `NODE_MCP_SECRET_KEY`. An altered or compromised dependency could read this value using ordinary process environment access. This is a supply-chain exposure rather than evidence that the currently linked package is malicious. ### Attack Path 1. An attacker compromises an upstream package release, installation source, or executable directory, or places a malicious executable named `zoom-phone-mcp` earlier in the runtime executable search path. 2. The skill invokes `mcporter` with `zoom-phone-mcp` as th ...[truncated 1341 chars]
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.