ClawHub
Back to skill

Security audit

Officecli

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent Office-document CLI helper, but its install instructions run remote scripts directly in the shell without integrity checks.

Review the installer source and trust the officecli.ai download endpoint before installing. Prefer a versioned release, package manager, checksum, or signature if available. Once installed, use the tool only on documents you intend to inspect or modify, and be aware that watch/resident modes start local helper services.

SkillSpector

By NVIDIA
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
Findings (1)

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The skill instructs users to install software by piping a remotely fetched script directly into a shell (`curl ... | bash` and `irm ... | iex`). This bypasses basic review and integrity checks, so a compromised download endpoint, DNS, CDN, or upstream release process could lead to immediate arbitrary code execution on the user's machine.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.