The Agent Skills Directory

[SAFE]: The skill is entirely instructional, providing guidelines and templates for email marketing sequences. No malicious patterns, remote code execution, or persistence mechanisms were detected. The skill focuses on marketing strategy, copy structure, and sequence timing.
[PROMPT_INJECTION]: The skill includes instructions to read from local context files like ".agents/product-marketing.md". While this represents a data ingestion point, it is a standard functional pattern for context-aware agents to personalize output based on project documentation. This ingestion is noted as a surface for indirect prompt injection if the context files are sourced from an untrusted third party, but no malicious intent was found in the skill's instructions.

emails