email-sequence

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists of Markdown-based guidelines and templates. It references well-known technology services like Mailchimp, Resend, and SendGrid for implementation guidance, which are considered trusted resources.
  • [NO_CODE]: No functional code, such as Python or JavaScript scripts, is included in the skill. All logic is provided via natural language instructions for the agent.
  • [PROMPT_INJECTION]: The skill instructions specify reading a local context file (e.g., .agents/product-marketing-context.md) to personalize email content. While this is an ingestion point for external data, it is a standard design pattern for marketing agents and does not grant the skill additional system permissions.
  • Ingestion points: SKILL.md (Initial Assessment section)
  • Boundary markers: None specified for the content of the context file.
  • Capability inventory: Limited to text generation (email copy); no subprocess, file-write, or network capabilities are present in the skill files.
  • Sanitization: No validation or sanitization of the context file content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 09:14 AM