ClawHub
Back to skill

Security audit

Skill Creator 0.1.0

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only guide for creating skills, with no hidden code, credential access, or automatic execution behavior.

Safe to install as a skill-writing guide. Because it helps create persistent agent skills, review any generated SKILL.md files, scripts, assets, and packaged skills before using or publishing them.

SkillSpector

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 (2)

Self-Modification

High
Category
Rogue Agent
Content
1. Understand the skill with concrete examples
2. Plan reusable skill contents (scripts, references, assets)
3. Initialize the skill (run init_skill.py)
4. Edit the skill (implement resources and write SKILL.md)
5. Package the skill (run package_skill.py)
6. Iterate based on real usage
Confidence
83% confidence
Finding
This section explicitly directs the agent to create and modify skill contents, including running initialization and packaging scripts and writing SKILL.md. In an environment where skills are part of the agent's trusted behavior surface, instructions for self-modification or creating new agent capabilities can expand functionality without sufficient review, increasing the risk of persistence or policy circumvention through generated skills.

Self-Modification

High
Category
Rogue Agent
Content
Any example files and directories not needed for the skill should be deleted. The initialization script creates example files in `scripts/`, `references/`, and `assets/` to demonstrate structure, but most skills won't need all of them.

#### Update SKILL.md

**Writing Guidelines:** Always use imperative/infinitive form.
Confidence
88% confidence
Finding
The instruction to update SKILL.md is a direct self-modification primitive: it tells the agent to alter the instructions that govern future agent behavior. Even though framed as normal skill authoring, modifying instruction files can be dangerous because it enables persistence of new behaviors, accidental weakening of safeguards, or insertion of unsafe triggers that affect future executions.

Static analysis

No suspicious patterns detected.