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