ClawHub

Agent Architecture Designer

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward architecture-advice skill with broad routing language but no evidence of hidden, destructive, or credential-seeking behavior.

Install this if you want an architecture specialist that may create or modify prototype code and run validation commands when asked. Consider narrowing the trigger wording if you only want it used for explicit system design, API design, scaling, or ADR work.

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
94% confidence
Finding
The frontmatter description says to use the skill when requests 'match this domain or role,' which is broad and lacks concrete boundaries. In agent routing systems, ambiguous activation criteria can cause the skill to be invoked for loosely related requests, leading to inappropriate tool access, unnecessary task delegation, or architectural recommendations outside the intended scope.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The 'When to Use' guidance only states that the skill applies when work matches the specialist role, but it does not specify when the skill should not be used or how to distinguish architecture work from adjacent domains. In practice, this can cause over-selection of the skill and expand the use of high-capability tools like Bash, WebFetch, and Write in situations where they are unnecessary or risky.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal