stitch-scenario-skill-creator
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a local Python script (
scripts/init_stitch_skill.py) to automate the creation of new skill directories and files. The script safely handles user-provided scenario names by validating them against a restrictive regular expression (r"stitch-ui-[a-z0-9]+(?:-[a-z0-9]+)*-designer"), which prevents path traversal or shell injection attacks. - [DATA_EXPOSURE]: No hardcoded credentials, API keys, or access to sensitive local file paths (such as SSH keys or environment files) were identified. The skill operates within its own directory structure.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests user input to generate new prompt templates, it applies strict character filtering and formatting. The generated output is written to new files rather than being directly executed in the current session's prompt context, minimizing the risk of immediate injection.
- [EXTERNAL_DOWNLOADS]: The documentation mentions an
npxcommand for adding related skills. This is provided as a reference for the user and is not executed automatically by the skill. The target package is associated with the skill's official vendor.
Audit Metadata