create-text-document

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns were detected. The skill consists entirely of markdown-formatted instructions for document structure and writing style.
  • [Indirect Prompt Injection] (LOW): The skill involves a tool call createDocument that takes user-provided content. While there are no explicit boundary markers or sanitization steps mentioned in this specific file, the skill itself does not perform dangerous operations with the data.
  • Ingestion points: User input is used for the 'content' parameter in the createDocument tool call.
  • Boundary markers: Not present in the instruction set.
  • Capability inventory: The skill uses a createDocument tool which appears to be for text output/storage.
  • Sanitization: None described in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:39 PM