skill-creator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The documentation describes platform features for installing plugins from Git repositories and URLs. These examples are for educational purposes and do not represent a vulnerability within the skill itself.
- [Data Exposure & Exfiltration] (SAFE): The skill provides guidance on managing credentials using environment variables and correctly uses placeholders (e.g., 'ghp_xxxx') in documentation. No real secrets or data exfiltration logic were found.
- [Command Execution] (SAFE): The provided Python utilities (package_skill.py and quick_validate.py) perform controlled file operations like zipping and text validation. They do not invoke arbitrary or untrusted shell commands.
- [Indirect Prompt Injection] (SAFE): The skill documentation describes how to ingest plugin data but the skill itself does not process untrusted external content at runtime, and it provides guidance on using explicit subagent delegation to maintain control.
Audit Metadata