stitch-vue-bootstrap-components
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes a bash script located at
scripts/fetch-stitch.shto download design assets (HTML and screenshots) from remote URLs. These URLs are provided dynamically by thestitch-mcp-get-screentool. - [COMMAND_EXECUTION]: The agent is instructed to use the
Bashtool to execute thefetch-stitch.shscript and manage project environments usingnpm install. - [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection (Category 8):
- Ingestion points: The skill downloads external HTML content into the agent's workspace via
scripts/fetch-stitch.sh. - Boundary markers: There are no instructions for the agent to use delimiters or ignore instructions embedded within the downloaded HTML during the conversion process.
- Capability inventory: The agent has
Bash,Write, andReadcapabilities, which could be exploited if the agent follows instructions hidden in the design files. - Sanitization: The skill does not define any sanitization or validation steps for the fetched HTML before it is parsed and used to generate component code.
Audit Metadata