obsidian-canvas-creator

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions and referenced documents focus exclusively on text-to-JSON transformation. There are no instructions for network access, shell command execution, or sensitive data handling.
  • [SAFE]: All external URLs point to official repositories and documentation for the Obsidian ecosystem (e.g., jsoncanvas.org, obsidianmd/jsoncanvas) or are provided as benign placeholder examples.
  • [SAFE]: The skill processes untrusted user data but implements structural validation and character escaping rules to ensure output integrity. While this provides a surface for indirect prompt injection, no capability for the agent to execute instructions contained within the input data is present in the skill's design.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 05:05 PM
Security Audit — agent-trust-hub — obsidian-canvas-creator