frontend-slides

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses platform-specific commands (open, xdg-open, start) to display generated HTML files in the default browser.\n- [COMMAND_EXECUTION]: Executes python3 to run scripts for PowerPoint content extraction and may use browser automation tools to validate layouts.\n- [EXTERNAL_DOWNLOADS]: Facilitates the installation of the python-pptx library from official repositories to handle PowerPoint file conversion.\n- [PROMPT_INJECTION]: An indirect prompt injection surface is present via the processing of untrusted PowerPoint (.ppt, .pptx) files, which could contain instructions designed to subvert the agent's generation logic.\n
  • Ingestion points: External .ppt and .pptx files.\n
  • Boundary markers: None specified to isolate file content from instructions.\n
  • Capability inventory: Shell command execution, Python execution, and file system write access.\n
  • Sanitization: No explicit content sanitization or instruction-filtering logic is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 07:42 AM
Security Audit — agent-trust-hub — frontend-slides