email-drafter

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOW
Full Analysis
  • [SAFE] (SAFE): The skill consists entirely of natural language instructions and email templates. No executable code (Python, Node.js, Shell), network calls, or sensitive file system interactions were detected.
  • [Indirect Prompt Injection] (LOW): The skill is designed to process user-provided context for drafting emails. While it lacks explicit input sanitization or boundary markers, it has no destructive capabilities or side-effect tools (such as automated sending or file modification), making the risk of exploitation negligible.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 08:49 PM