The Agent Skills Directory

[SAFE]: The skill is primarily instructional and contains no executable code or scripts that perform dangerous operations. It explicitly refuses requests to bypass authentication or impersonate users.\n- [EXTERNAL_DOWNLOADS]: The skill recommends installing related modular skills using the npx skills add command. These references point to the same vendor ('full-stack-skills') and represent legitimate modular extensions of the same framework.\n- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for mapping authentication frameworks to a domain model. It includes robust guidance on implementing security boundaries, using type-safe getters, and ensuring proper context cleanup to prevent identity residue, effectively addressing potential injection surfaces through secure design patterns.

ddd4j-auth