ClawHub
Back to skill

Security audit

Harness Dev Standards

Security checks across malware telemetry and agentic risk

Overview

This is a coherent code-quality skill, but it gives agents broad automatic authority to edit dependencies/code and force-stop local processes without clear approval or rollback controls.

Install only if you want an agent to actively help enforce development standards. Use it in trusted repositories, review package scripts first, and instruct the agent to ask before editing files, changing dependencies, installing global tools, creating .env files, running dev/build commands, or killing processes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (4)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The invocation guidance is extremely broad, covering common activities like starting a project, pre-delivery checks, standardizing workflow, architecture review, code review, and dependency/environment troubleshooting. In an agent setting, this can cause the skill to trigger in many ordinary development contexts and over-apply its recommendations, including its auto-remediation behavior, beyond the user's explicit intent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs automatic remediation for dependency, import, syntax, startup, and type issues, including modifying versions or removing dependencies, without requiring user approval or warning about side effects. This is dangerous because an agent could silently alter code or dependency state, introduce regressions or supply-chain risk, and repeatedly apply changes until 'resolved' without a defined safety boundary.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The document instructs users to run `kill -9 <PID>` after identifying a process on port 3000, but it does not warn about verifying the target process or the risk of terminating unrelated services. In an automated remediation context, destructive commands without safety guardrails can cause denial of service or data loss if applied to the wrong process.

Missing User Warnings

Low
Confidence
78% confidence
Finding
The verification workflow repeatedly instructs execution of commands such as type-checking, linting, starting the project, and building without warning that they may modify the workspace, install dependencies indirectly, or expose local network services. In a skill meant for automated repair, this can encourage unsafe execution patterns and unexpected side effects.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.