ClawHub

Architecture Review

Security checks across malware telemetry and agentic risk

Overview

This is a coherent architecture-review skill with broad activation wording, but no hidden code, persistence, credential access, or destructive behavior was found.

Install this if you want an architecture-audit workflow. Before using it, confirm the review scope and approve any follow-on refactoring or agent-team actions, especially in private repositories or when npx tools may be downloaded and executed.

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
95% confidence
Finding
The trigger conditions are broad enough to match common requests like "audit this project" or simply entering an unfamiliar repository, which can cause the skill to activate outside the user's intended scope. In an agent system, overbroad activation can lead to unexpected tool execution, unnecessary repository scanning, and chaining into other skills such as refactoring or agent orchestration without clear user consent.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The command trigger list is ambiguous and uses generic phrases such as "看看代码有没有问题", which can overlap with requests for debugging, security review, or general code help rather than architecture review specifically. This raises the risk of unintended activation and misrouting, especially because the skill can recommend or trigger follow-on skills based on its findings.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal