skills/markdown-viewer/skills/cloud/Gen Agent Trust Hub

cloud

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of Markdown documentation and PlantUML code examples. It does not include any scripts, binaries, or automated command execution logic.
  • [SAFE]: No network operations, external downloads, or data exfiltration patterns were detected. The skill references local documentation and standard PlantUML stencil libraries for visualization.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a framework for the agent to process user-provided architecture descriptions into diagrams.
  • Ingestion points: User-provided cloud architecture requirements.
  • Boundary markers: The skill instructs the agent to wrap all output in specific ```plantuml or ```puml code fences.
  • Capability inventory: None; the skill does not use any tools or execute any shell commands.
  • Sanitization: Not applicable, as the skill only produces text output for rendering.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:40 AM
Security Audit — agent-trust-hub — cloud