ClawHub
Back to skill

Security audit

Skill Builder

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward guide for creating agent skills, with no hidden execution, credential access, network behavior, or self-installing code.

Install if you want an agent-facing checklist for creating skills. Before using any generated skill, review its requested tools and install location, because newly created skills can affect future agent behavior once placed in a persistent skills directory.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Self-Modification

High
Category
Rogue Agent
Content
Use when: Complex domain, multiple sub-capabilities, utility scripts needed.

### Phase 3: Write SKILL.md

#### Frontmatter Requirements
Confidence
26% confidence
Finding
Write SKILL

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.