The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local bash script, scripts/fetch-stitch.sh, to handle asset retrieval.
[EXTERNAL_DOWNLOADS]: The skill performs network downloads of design HTML and screenshots from external URLs provided by the Stitch MCP tools (typically hosted on Google Cloud Storage).
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted design metadata and HTML code, which creates a potential surface for indirect prompt injection if the design source is malicious.
Ingestion points: Data retrieved from stitch-mcp-get-screen and the HTML content downloaded to temp/source.html.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the processing logic.
Capability inventory: The skill possesses shell execution capabilities via Bash and file system access via Read and Write tools.
Sanitization: There is no evidence of input validation or sanitization for the design assets before they are processed by the agent.

stitch-uview-components