emails
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown-based instructions, strategic frameworks, and copy templates for email marketing. It does not include executable scripts, subprocess calls, or mechanisms for persistence.
- [SAFE]: External tool references point to well-known email marketing services (e.g., Mailchimp, SendGrid) and internal project documentation, representing standard integration patterns for content generation agents.
- [PROMPT_INJECTION]: The skill is designed to ingest user-provided context regarding products and target audiences to generate email copy, presenting an indirect prompt injection surface. Ingestion points: User-supplied answers to assessment questions in SKILL.md. Boundary markers: None present. Capability inventory: The skill is restricted to text generation and lacks tools for file system modification, network exfiltration, or command execution. Sanitization: None present. The risk is assessed as safe due to the absence of exploitable capabilities.
Audit Metadata