agent-prompt

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is primarily educational documentation, providing instructions and best practices for prompt engineering without including executable scripts or logic.
  • [NO_CODE]: No code or external dependencies are included in this skill; it consists solely of a markdown file with instructional content.
  • [SAFE]: The provided templates emphasize security best practices, such as explicitly defining prohibited actions (e.g., 'STRICTLY PROHIBITED from...'), implementing read-only modes, and verifying user identity before processing requests.
  • [SAFE]: Examples involving database tools (e.g., list_tables, describe_table) and specific SQL functions (e.g., TD_INTERVAL) are consistent with the vendor's (Treasure Data) infrastructure and intended use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 11:38 AM