frontend-slides
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted PowerPoint files which may contain instructions designed to influence the agent behavior (Indirect Prompt Injection).
- Ingestion points: Extracts text, images, and notes from .ppt and .pptx files as described in the PowerPoint Conversion section of SKILL.md.
- Boundary markers: No specific delimiters or instructions are used to separate the extracted content from the agent's logic.
- Capability inventory: The skill executes Python scripts, writes local files, and runs shell commands to open the browser.
- Sanitization: No sanitization of the extracted PowerPoint content is specified before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill uses OS-specific shell commands such as 'open', 'xdg-open', and 'start' to launch the generated HTML files.
- [EXTERNAL_DOWNLOADS]: The skill suggests the installation of the 'python-pptx' library, which is a standard and well-known Python package for handling PowerPoint files.
Audit Metadata