stitch-ui-uview-plus-components
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a shell script
scripts/fetch-stitch.shto manage design asset downloads and local storage. - [DATA_EXFILTRATION]: The skill performs network operations via
curlto fetch design content from the Google Stitch service. - [INDIRECT_PROMPT_INJECTION]: Converting external design metadata and HTML into application code presents a vulnerability surface for indirect prompt injection.
- Ingestion points: HTML content and design JSON retrieved from external Stitch URLs.
- Boundary markers: None are defined to isolate external data from internal logic.
- Capability inventory: Includes file system access for writing components, execution of local bash scripts, and tool calls.
- Sanitization: The skill does not implement sanitization for the design data before processing.
Audit Metadata