The Agent Skills Directory

[SAFE]: The skill operates entirely within the provided instructions and local project context. It references specific files like .agents/product-marketing.md to gather relevant business context, which is a standard and safe practice for AI agents.
[SAFE]: There are no network requests, data exfiltration patterns, or hardcoded credentials detected in the skill body or reference files.
[SAFE]: The instruction set does not contain any obfuscated code, hidden instructions, or prompt injection attempts. The use of persona-setting ("You are an expert conversion copywriter") is standard for directing LLM behavior.
[SAFE]: No remote code execution or external dependency risks were identified. The skill relies solely on internal markdown references for its frameworks and templates.

copywriting