emails
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill package is composed strictly of Markdown documentation and JSON evaluation data. No executable scripts, binaries, or configuration files that trigger code execution (such as .py, .js, or .sh files) are included.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external context files (e.g., .agents/product-marketing.md) and user-supplied prompts to generate automated email copy.
- Ingestion points: .agents/product-marketing.md and user-provided task descriptions.
- Boundary markers: None identified in the skill instructions.
- Capability inventory: The skill integrates with email automation tools (e.g., Resend, Mailchimp, Nitrosend) via standard MCP tool references to implement sequences.
- Sanitization: The instructions do not specify any validation or sanitization for the ingested context data.
Audit Metadata