ClawHub
Back to skill

Security audit

orbcafe-ui-component-usage

Security checks across malware telemetry and agentic risk

Overview

This skill is a documentation-only ORBCAFE UI router that gives setup and module-selection guidance without hidden data access or automatic execution.

Install this only if you want help with ORBCAFE UI integration. Review the companion ORBCAFE module skills it routes to, and run the npm/build commands only in the intended project after checking package names and versions.

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 (1)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The routing map uses very broad keywords such as "layout", "detail", "assistant", and "chat" to select downstream skills. In an agentic system, ambiguous keyword triggers can cause the wrong skill to be invoked, leading to unintended capability exposure, mis-scoped actions, or bypass of stricter module-specific guidance when a user prompt matches multiple categories.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.