stitch-vue-bootstrap-components
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads HTML design files from remote URLs provided by the Stitch MCP tool, typically hosted on Google Cloud Storage. This operation is central to the skill's purpose of processing design assets.
- [COMMAND_EXECUTION]: The skill uses a bash script (scripts/fetch-stitch.sh) to run curl for downloading data. It also instructs the agent to perform standard development tasks like npm install and npm run dev to initialize and test the generated Vue project.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of external HTML content.
- Ingestion points: Data enters the agent context through the temp/source.html file, which is fetched from external download URLs.
- Boundary markers: The instructions do not define specific delimiters or security warnings to prevent the agent from following instructions that might be embedded in the design HTML.
- Capability inventory: The agent possesses Bash, Read, and Write capabilities, allowing it to execute scripts and modify the local filesystem based on its interpretation of the data.
- Sanitization: There are no documented procedures for sanitizing or validating the fetched HTML before it is parsed for component generation.
Audit Metadata