email-drafter

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely composed of instructional text and examples for an AI agent to draft emails. It does not involve any command execution, file system access, or network requests.
  • [NO_CODE]: There are no scripts, code snippets, or configuration files that could be executed at runtime.
  • [PROMPT_INJECTION]: The instructions are clear and purpose-driven, with no attempts to bypass safety filters or override system-level instructions.
  • [DATA_EXFILTRATION]: No network tools or sensitive data access patterns are present. The skill operates solely on text generation based on user-provided contexts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 04:46 PM
Security Audit — agent-trust-hub — email-drafter