The Agent Skills Directory

[SAFE]: The skill content is restricted to instructional guidance on marketing and user experience. No malicious code, prompt injections, or unauthorized data access patterns were identified during the analysis of the instructions and reference materials.
[INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read local context files like .agents/product-marketing.md to inform its recommendations. While this involves reading external files, it is a standard practice for context-aware agents and does not present a risk here as the skill lacks capabilities for code execution or network exfiltration based on that content.

onboarding