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, and start to display the generated HTML presentation files to the user, and it executes local Python scripts via python3 for PowerPoint content extraction.
  • [EXTERNAL_DOWNLOADS]: The skill suggests the installation of the python-pptx library from the Python Package Index to facilitate the conversion of presentation files into HTML format.
  • [PROMPT_INJECTION]: The skill processes external .ppt and .pptx files as seen in SKILL.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 in SKILL.md. Sanitization: Absent; the skill extracts text and images directly for inclusion in the HTML output without explicit sanitization or filtering logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 04:01 AM
Security Audit — agent-trust-hub — frontend-slides