email-design
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill follows security best practices by explicitly instructing the agent to keep sensitive data like tokens and addresses private.
- [INDIRECT_PROMPT_INJECTION]: The skill manages the risk of processing untrusted data (app copy and user-supplied fields) through a defined security posture:
- Ingestion points: App themes and message content processed in SKILL.md.
- Boundary markers: Instructions to limit per-message content and use specific placeholders.
- Capability inventory: No dangerous system or network capabilities are present.
- Sanitization: Mandatory use of escaping template engines and destination validation.
- [EXTERNAL_DOWNLOADS]: The skill references external documentation from Mailchimp regarding HTML email structure and accessibility. These are well-known resources from a reputable service provider and are documented neutrally.
Audit Metadata