ClawHub
Back to skill

Security audit

Xlsx

Security checks across malware telemetry and agentic risk

Overview

This spreadsheet skill is coherent and disclosed, though users should be careful with workbook edits and LibreOffice recalculation on untrusted files.

Install only if you want an agent to inspect and manipulate spreadsheet files. Use copies or explicit output filenames for important workbooks, and avoid running LibreOffice recalculation on spreadsheets from untrusted sources unless the environment is appropriately isolated.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
elif platform.system() == "Darwin" and has_gtimeout():
            cmd = ["gtimeout", str(timeout)] + cmd

        result = subprocess.run(
            cmd, capture_output=True, text=True, env=get_soffice_env()
        )
Confidence
87% confidence
Finding
result = subprocess.run( cmd, capture_output=True, text=True, env=get_soffice_env() )

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs the agent to execute shell commands and write files (`inspect.py`, `recalc.py`, workbook saves) but does not declare corresponding permissions. This creates a capability/permission mismatch that can lead to unsafe execution assumptions, reduce sandbox visibility, and enable unintended file modification or command execution when the skill is invoked.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger is extremely broad ('any time a spreadsheet file is the primary input or output'), making the skill likely to activate on many common requests. Overbroad activation increases the chance that risky file-writing or shell-based behaviors are applied in situations where the user did not clearly request modification, causing unintended edits or unnecessary execution of local tooling.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill provides direct edit/write workflows for existing spreadsheets, including row/column insertion, deletion, saving, and recalculation, without requiring backup creation, confirmation, or warning about destructive changes. In a file-handling skill, this omission is dangerous because users may lose data, corrupt formulas, or overwrite important business documents through normal use rather than overt exploitation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.