ClawHub
Back to skill

Security audit

tax-filing

Security checks across malware telemetry and agentic risk

Overview

This tax-preparation skill appears purpose-aligned, but it may activate too broadly and asks for highly sensitive tax and immigration information without clear privacy limits.

Review this skill before installing. Use it only for explicit tax-preparation tasks, avoid uploading or pasting full identifiers unless necessary, redact documents where possible, and confirm that you are comfortable sharing tax, residency, and travel-history details with the agent environment.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger text is extremely broad ('whenever the user mentions taxes' and similar phrases), which can cause the skill to activate in conversations that are only loosely related to filing. Because this skill handles highly sensitive financial and immigration-related data and may guide form completion, over-triggering increases the risk of unnecessary collection, exposure, or processing of sensitive information in the wrong context.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs collection and handling of tax records, visa/travel history, and IRS form data without an explicit privacy warning, minimization guidance, or consent checkpoint. In this context, the data includes highly sensitive personal, financial, and immigration information, so users may disclose more than necessary without understanding the sensitivity or retention implications.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.