stitch-manage-design-system
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill does not exhibit any malicious behavior and includes explicit safety guidelines, such as an anti-pattern against storing API keys.
- [COMMAND_EXECUTION]: The skill uses a local script (scripts/upload_to_stitch.py) for data transfer, which is a documented functional requirement for the Stitch platform integration.
- [PROMPT_INJECTION]: The skill processes user-supplied design files, creating a surface for indirect prompt injection that is mitigated by specific verification protocols and anti-pattern warnings.
Audit Metadata