deck-studio

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a secure human-in-the-loop workflow, specifically requiring user confirmation of an outline before proceeding to more complex visual or content generation steps.
  • [SAFE]: All included scripts (generate.js, assemble.js) are transparently coded for local document generation (HTML to PPTX) and do not contain hidden network calls, data exfiltration, or obfuscation.
  • [SAFE]: The skill explicitly defines execution boundaries in the documentation, instructing the agent to avoid unauthorized network access or sensitive file operations.
  • [SAFE]: External dependencies mentioned, such as pptxgenjs and markitdown, are well-known, legitimate software libraries appropriate for the skill's stated purpose.
  • [SAFE]: References to external repositories and design archives (e.g., github.com/staruhub/ClaudeSkills and otlaicher.de) are contextual to the developer's infrastructure and the skill's design methodology.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 06:29 AM
Security Audit — agent-trust-hub — deck-studio