obi-notes

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to manage the local filesystem by creating directories and writing markdown files in the user's Documents folder.
  • [PROMPT_INJECTION]: The skill processes untrusted data from the user and the system clipboard to determine file organization and content, which is a surface for indirect prompt injection.
  • Ingestion points: User-supplied text and clipboard content.
  • Boundary markers: Absent. There are no explicit delimiters to isolate untrusted user content.
  • Capability inventory: Local file system writes and directory creation.
  • Sanitization: None detected. User data is interpolated directly into templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 12:08 PM
Security Audit — agent-trust-hub — obi-notes