stitch-code-to-design
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The description uses directive language ("ALWAYS use this skill", "must use this skill") to steer agent behavior and ensure this specific workflow is prioritized over default actions for saving or migrating code.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and process untrusted frontend source code, serving as a vector for indirect prompt injection.
- Ingestion points: Frontend project source code, including templates and component files.
- Boundary markers: No explicit delimiting or instructions to ignore embedded commands are present in the workflow.
- Capability inventory: The skill has access to shell execution via Bash and file system operations via Read and Write tools.
- Sanitization: The skill does not mention validation or sanitization of the code being analyzed.
- [COMMAND_EXECUTION]: The workflow relies on executing Bash commands and platform-specific scripts to automate the extraction and upload of application data.
Audit Metadata