claude-artifact-creator
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a meta-tool for project organization, defining a three-layer knowledge architecture (Concepts, Implementations, and Skills). This structure promotes modularity and follows development best practices.
- [COMMAND_EXECUTION]: The skill documents the use of local Python scripts (e.g.,
scripts/init_skill.py,scripts/validate.py) for initializing and validating project files. These scripts are assumed to be part of the user's local repository and no remote downloads are initiated. - [PROMPT_INJECTION]: The content includes instructions on how to write effective agent descriptions and triggers. While these manipulate agent behavior, they are functional guidelines for the skill's purpose and do not contain bypass or jailbreak attempts.
Audit Metadata