obsidian-canvas-creator
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Indirect Prompt Injection] (LOW): 1. Ingestion points: Workflow Step 1 in SKILL.md reads untrusted user text. 2. Boundary markers: Absent. 3. Capability inventory: Limited to structured JSON output; no subprocess, file-write, or network calls identified across any files. 4. Sanitization: JSON validation checklist and quote escaping rules in SKILL.md. Risk is negligible due to the absence of side-effect capabilities.
- [Data Exposure & Exfiltration] (SAFE): No access to sensitive file paths, hardcoded credentials, or unauthorized network operations detected.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No patterns for external script downloads or runtime execution of untrusted code were identified.
- [Obfuscation] (SAFE): The documented use of Chinese character quotes for Obsidian compatibility is a data-level transformation for character encoding and does not constitute a malicious concealment technique.
Audit Metadata