frontend-slides
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill generates and executes a Python script to extract content from PowerPoint files using the 'python-pptx' library. It also instructs the agent to use the 'open' command to launch the resulting HTML files in the browser for user review.
- [EXTERNAL_DOWNLOADS]: The skill fetches CSS and font assets from established and trusted providers, including Google Fonts and Fontshare (api.fontshare.com), to style the generated presentations.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection through its PowerPoint conversion feature. 1. Ingestion points: Content is extracted from user-supplied .pptx files in SKILL.md. 2. Boundary markers: No specific delimiters or instructions are used to separate extracted content from the agent's internal logic. 3. Capability inventory: The agent has the ability to execute Python scripts, run shell commands (open), and write to the file system. 4. Sanitization: No validation or sanitization is performed on the text extracted from slide shapes or notes before it is processed.
Audit Metadata