ClawHub
Back to skill

Security audit

officecli-financial-model

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly provides legitimate Excel financial-modeling guidance, but its setup instructions ask users or agents to run unverified remote installer code.

Install only if you are comfortable with officecli and verify the installer source yourself. Prefer a pinned release, package-manager install, or manually downloaded binary with checksum/signature verification instead of allowing an agent to run the pipe-to-shell setup command automatically.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill includes setup instructions to fetch and execute remote installer scripts and to download binaries from the internet, which is not necessary to explain how to build a financial model in Excel. Embedding installation guidance in a skill increases the chance that an agent or operator performs network and code-execution actions beyond the user's modeling request, expanding the attack surface and enabling supply-chain compromise if the remote endpoint is malicious or later compromised.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The commands `curl ... | bash` and `irm ... | iex` execute code fetched over the network immediately, without integrity verification, pinning, or an explicit warning. This is a classic supply-chain and remote code execution risk: if the host, DNS, TLS trust chain, or distribution pipeline is compromised, anyone following the skill can run attacker-controlled code on their 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
The skill explicitly instructs fetching a remote shell script and piping it into `bash`, which is unsafe by design because untrusted network content is executed immediately on the host. In skill context this is especially dangerous because the task is spreadsheet modeling, so remote script execution is unrelated to the core user intent and represents unjustified privilege expansion.

Static analysis

No suspicious patterns detected.