skills/xberg-io/xberg/pptx/Gen Agent Trust Hub

pptx

Pass

Audited by Gen Agent Trust Hub on May 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses established, reputable libraries such as markitdown (developed by Microsoft), Pillow, and pptxgenjs for PowerPoint processing and slide generation.
  • [SAFE]: Commands for file manipulation (unpacking, editing) and visual verification (converting to images) follow standard developer workflows and utilize well-known utilities like LibreOffice and Poppler (pdftoppm).
  • [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found in the analyzed instructions. Instructional content in the QA section is designed to improve output quality through subagent verification.
  • [SAFE]: The skill processes untrusted .pptx files, creating a standard data ingestion surface.
  • Ingestion points: .pptx files referenced in command lines (e.g., presentation.pptx, output.pptx) within SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: Shell command execution via python, grep, and pdftoppm (SKILL.md).
  • Sanitization: Absent.
  • Analysis: The workflow involves standard text extraction and slide-to-image conversion consistent with the skill's stated purpose, with no risky patterns identified in the execution logic.
Audit Metadata
Risk Level
SAFE
Analyzed
May 21, 2026, 08:51 PM
Security Audit — agent-trust-hub — pptx