frontend-slides
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses operating system commands such as
open,xdg-open, andstartto display the generated HTML presentation files to the user, and it executes local Python scripts viapython3for PowerPoint content extraction. - [EXTERNAL_DOWNLOADS]: The skill suggests the installation of the
python-pptxlibrary from the Python Package Index to facilitate the conversion of presentation files into HTML format. - [PROMPT_INJECTION]: The skill processes external
.pptand.pptxfiles as seen inSKILL.md, which introduces a surface for Indirect Prompt Injection. Ingestion points: External PowerPoint files provided by the user. Boundary markers: Absent; the skill does not use delimiters or instructions to ignore content-embedded commands. Capability inventory: File system write (presentation.html), subprocess execution (python3), and OS-level command execution (open,start,xdg-open) as defined inSKILL.md. Sanitization: Absent; the skill extracts text and images directly for inclusion in the HTML output without explicit sanitization or filtering logic.
Audit Metadata