ClawHub
Back to skill

Security audit

Simple Code

Security checks across malware telemetry and agentic risk

Overview

This is a coding-workflow instruction skill that can edit project files and keep local notes, but those actions are disclosed and fit its purpose.

Install this if you want an agent workflow for small coding tasks. Use it in a version-controlled project, specify the target path, say 'review only, do not patch' when you only want feedback, and remember that .steps notes and delegated sub-agent work may include project context.

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 skill instructs the agent to infer invocation from very broad terms such as 'add', 'change', 'improve', 'review', and 'create'. In a larger routing system, these generic phrases are common in ordinary user requests, so the skill could be activated unintentionally and take project-modifying actions in contexts where the user did not explicitly request this skill.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.