skill-creator
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Instructions in SKILL.md direct the agent to execute provided Python scripts (scripts/init_skill.py and scripts/package_skill.py) to automate the skill development lifecycle.
- [DYNAMIC_EXECUTION]: The scripts/init_skill.py script generates boilerplate content, including a Python script (scripts/example.py), from hardcoded text templates to provide a starting point for new skills.
- [INDIRECT_PROMPT_INJECTION]: As a meta-skill designed to generate instructions for other agents based on user-defined behaviors, it creates a pipeline where user input directly influences the instructions generated for downstream agents.
Audit Metadata