skill-creator
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill's instructions and documentation are focused on development best practices and do not contain any prompt injection or deceptive content intended to override agent behavior.
- [COMMAND_EXECUTION]: The skill contains Python scripts (
init_skill.py,package_skill.py) that perform local file system operations, including directory creation and file zipping. These activities are essential for the skill's primary purpose and do not involve unauthorized shell command execution or network access. - [SAFE]: The included scripts utilize secure programming practices, such as using
yaml.safe_loadfor parsing configuration files and relying on standard Python libraries (pathlib,zipfile) for file handling. - [SAFE]: No evidence of obfuscation, hardcoded credentials, or remote code execution was found across any of the skill's files or resources.
Audit Metadata