ClawHub

amis-ui

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a purpose-aligned AMIS UI JSON/template generator with only minor auto-activation ambiguity.

Install this if you want help generating AMIS JSON UI definitions. If your agent auto-loads skills from generic requests, explicitly choose or avoid this skill when building non-AMIS UI, and review generated templates before deploying because some examples include placeholder login, create, update, and delete API actions.

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
83% confidence
Finding
The README shows broad, everyday requests such as generating a user management page as automatic triggers, but it does not define clear activation boundaries or disambiguation rules. In agent environments, this can cause the skill to activate on generic UI-related prompts unexpectedly, increasing the chance of over-broad prompt injection into workflows or unintended behavior selection.

Vague Triggers

Medium
Confidence
79% confidence
Finding
The direct-trigger example mixes explicit invocation with a natural-language request but does not specify when natural-language-only requests should invoke the skill. This ambiguity can cause accidental routing of unrelated or partially related prompts into the skill, which is risky in multi-skill systems because it broadens the skill's effective authority and attack surface.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal