skills/ethan-rio/skills/ai-slides/Gen Agent Trust Hub

ai-slides

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a guide for generating slide content. All code provided in the markdown file consists of illustrative Python and Bash snippets for educational purposes rather than executable scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied topics and outlines to generate presentations, which is a standard ingestion point for AI agents.
  • Ingestion points: User-provided topics and notes defined in the 'How to Use' section of SKILL.md.
  • Boundary markers: The skill does not explicitly define boundary markers for user input, but operates within the context of a presentation generation task.
  • Capability inventory: The skill utilizes create_pptx and add_slide via MCP tools to output presentation files.
  • Sanitization: Not explicitly implemented in the provided documentation, but the skill's primary function is content generation for review by the user.
  • [EXTERNAL_DOWNLOADS]: The skill references established presentation resources including Marp, Slidev, and reveal.js. These are well-known services and the skill does not automate their installation or execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 10:55 AM
Security Audit — agent-trust-hub — ai-slides