ClawHub
Back to skill

Security audit

Generate Immigration Law Firm Client Education Handout

Security checks across malware telemetry and agentic risk

Overview

The skill is a simple handout-writing package, but it grants broad shell and file-reading authority that is not explained by its drafting purpose.

Install only if you are comfortable with a drafting skill that declares Bash and local file-read access despite not explaining a need for them. Use it for general educational drafts only, provide minimal source material, avoid case-specific legal conclusions, and require review by a licensed immigration attorney before sending anything to clients.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill's invocation scope is broad enough that it could be selected for general client-education tasks without clear boundaries, increasing the chance it is used in inappropriate contexts. In a legal domain, accidental over-invocation is risky because users may receive authoritative-looking immigration guidance when a narrower, reviewed workflow should be required.

Natural-Language Policy Violations

Low
Confidence
87% confidence
Finding
The skill generates client-facing immigration law content but only briefly notes human review, which is insufficient for a sensitive legal domain. This can lead to unauthorized legal-advice-like output, inaccurate or outdated guidance, and client reliance on polished materials that appear professionally vetted.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.