ClawHub
Back to skill

Security audit

ai-architecture-harness-en

Security checks across malware telemetry and agentic risk

Overview

This skill is a repository-local architecture guardrail guide with no hidden execution, credential use, or external data handling evident.

Install this if you want an agent to help document and enforce architecture rules in a codebase. Review any suggested AGENTS.md, docs, tests, or lint changes like normal code changes, especially if the skill activates during a broad coding request.

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
88% confidence
Finding
The skill description contains broad trigger phrases such as "AI coding," "Agent coding," and general requests to make a codebase "safer," which can cause the skill to activate in many ordinary coding conversations outside its intended niche. Over-broad activation increases the chance of unsolicited architectural changes, document creation, or process imposition in contexts where the user did not ask for this behavior, which can degrade safety and reliability of agent actions.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.