emails
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional Markdown content and a JSON evaluation manifest. No executable scripts, binaries, or configuration files that trigger command execution were detected.
- [SAFE]: The skill references local context files (e.g.,
.agents/product-marketing.md) to inform its generation of email copy. This is a standard and safe method for an AI agent to gather necessary business context without exposing sensitive system information. - [SAFE]: In
references/guidelines.md, the skill lists several well-known third-party email services (such as Mailchimp, SendGrid, and Customer.io) as potential integrations. These are documented as informational references and do not include any commands for installation, credential handling, or automated exfiltration. - [SAFE]: No obfuscation, prompt injection attempts, or persistence mechanisms were found across any of the 12 analyzed files.
Audit Metadata