email-drip-sequence
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided product and audience information to generate marketing copy, which constitutes an indirect prompt injection surface.
- Ingestion points:
product.name,product.affiliate_url, andaudience.descriptioninput fields inSKILL.md. - Boundary markers: The instructions do not specify delimiters or protective instructions to isolate user-provided data from the agent's task logic.
- Capability inventory: The skill is restricted to text generation and does not have capabilities for shell access, network communication, or filesystem writing.
- Sanitization: No explicit sanitization or validation of the input strings is implemented.
- [SAFE]: The skill does not include any executable code, shell commands, or network operations. All external references point to internal project documentation or trusted vendor resources associated with the author 'affitor'.
Audit Metadata