ClawHub
Back to skill

Security audit

officecli-data-dashboard

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to disclose a purpose-aligned CLI dependency install, but users should avoid blindly piping remote installer scripts into a shell.

Before installing, prefer downloading a pinned OfficeCLI release from the project’s release page and verifying its checksum or signature if available. If you use the one-line installer, review the script first and run it only in an environment where you trust the publisher and the installer host.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs users to execute remote installer scripts directly via shell pipelines (`curl | bash`, `irm | iex`) without any integrity verification, review step, or warning. This is dangerous because a compromised download host, TLS-intercepting environment, or malicious upstream change would result in immediate arbitrary code execution on the user's machine.

External Script Fetching

High
Category
Supply Chain
Content
If `officecli` is missing:

- **macOS / Linux**: `curl -fsSL https://d.officecli.ai/install.sh | bash`
- **Windows (PowerShell)**: `irm https://d.officecli.ai/install.ps1 | iex`

Verify with `officecli --version` (open a new terminal if PATH hasn't picked up). If install fails, download a binary from https://github.com/iOfficeAI/OfficeCLI/releases.
Confidence
99% confidence
Finding
`curl -fsSL https://d.officecli.ai/install.sh | bash` is a classic arbitrary code execution pattern: it fetches code from the network and immediately executes it in the shell. In the context of an agent skill, this is especially dangerous because it normalizes unsafe behavior and could lead an operator or downstream agent to run attacker-controlled code with the user's privileges.

Static analysis

No suspicious patterns detected.