carrossel
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npm, npx, and node to manage dependencies and run the image export script.
- [EXTERNAL_DOWNLOADS]: The skill installs the playwright package from the official NPM registry and downloads the Chromium browser binary via npx playwright install.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content and interpolates it into an HTML template rendered by a headless browser. 1. Ingestion points: User responses during the interview phase in SKILL.md. 2. Boundary markers: The skill includes a step to show the generated copy to the user for approval before proceeding to file generation. 3. Capability inventory: Shell command execution (npm, node) and file system operations to create the working directory and HTML files. 4. Sanitization: No explicit sanitization or escaping of user-provided content is mentioned before interpolation into the HTML template.
Audit Metadata