stitch-to-react
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted HTML data from Google Stitch exports, creating a surface for indirect prompt injection.
- Ingestion points:
design-intent/google-stitch/{feature}/exports/*.html(referenced inSKILL.md). - Boundary markers: Absent. There are no instructions for the agent to ignore potentially malicious embedded instructions in the source HTML.
- Capability inventory: File reading/writing and shell globbing (documented in
SKILL.md). - Sanitization: Absent. The skill extracts content directly for code generation.
- [COMMAND_EXECUTION]: The skill instructs the agent to use shell-based glob commands to verify the existence of export files.
- Evidence:
Glob: design-intent/google-stitch/{feature}/exports/*.htmlinSKILL.md.
Audit Metadata