email-sequence
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the provided files. The skill functions as a knowledge base and instructional guide for the AI agent.
- [NO_CODE]: The skill does not include any executable scripts (such as Python, JavaScript, or Bash). All logic is contained within natural language instructions and markdown templates.
- [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection by instructing the agent to read context from external files like
.agents/product-marketing-context.md. While this ingestion of potentially untrusted data is a known vector, the lack of high-privilege tools or code execution capabilities in the analyzed files mitigates the risk. - Ingestion points: Local file
.agents/product-marketing-context.mdand user-provided prompts (SKILL.md). - Boundary markers: None present.
- Capability inventory: Primary capability is text generation for email copy; references to external tools (Mailchimp, Resend) are mentioned but not implemented via scripts in this package.
- Sanitization: None present.
Audit Metadata