frontend-slides
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes platform-specific shell commands (open, xdg-open, start) to launch generated HTML files.
- [EXTERNAL_DOWNLOADS]: The skill requests the installation of the 'python-pptx' library from the official Python package index.
- [PROMPT_INJECTION]: The skill processes untrusted user data, creating a surface for indirect prompt injection. Ingestion points: User-provided notes, drafts, and .pptx files. Boundary markers: No delimiters are present to separate user content. Capability inventory: Includes file system write access and shell command execution. Sanitization: No sanitization or escaping of user content is performed before interpolation into generated HTML/JS.
Audit Metadata