skill-creator-pro
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes Python scripts (
init_skill.py,package_skill.py) that perform legitimate file system operations. These include creating directories, writing template files, modifying file permissions (setting execution bits), and creating ZIP archives. These actions are consistent with the skill's stated purpose as a development utility. - [REMOTE_CODE_EXECUTION]: No remote code execution patterns or unverified external dependencies were found. The skill relies on standard Python libraries.
- [CREDENTIALS_UNSAFE]: No hardcoded credentials were detected. The skill includes documentation in
references/technical-patterns.mdthat explicitly advises against hardcoding secrets and recommends using environment variables. - [DATA_EXFILTRATION]: No network operations or data exfiltration patterns were identified. The scripts operate locally on the file system.
- [PROMPT_INJECTION]: The skill uses instructional language to guide the agent's behavior. No attempts to bypass safety filters or override core system instructions were detected.
- [SAFE]: The skill follows development best practices and provides security guidance (e.g., path traversal prevention and SQL injection awareness) for the skills it helps create.
Audit Metadata