local-axure-workflow
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local script
node scripts/check-app-ready.mjsto verify the state of generated pages. This represents a capability to run system commands, which may be vulnerable if paths or arguments are derived from unvalidated external data. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external files (sitemap.json, theme.json, content.md) to guide code generation and project structuring.
- Ingestion points: Processes sitemap.json, theme.json, and content.md from the local project directory.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the processed data are defined.
- Capability inventory: Includes file-writing to the local repository and execution of Node.js scripts.
- Sanitization: No visible mechanisms to sanitize or validate the content of the Axure export files before processing.
- [EXTERNAL_DOWNLOADS]: The skill includes functionality to use MCP tools for fetching online resources if a projectUrl is found in the local configuration, potentially allowing external network requests.
Audit Metadata