The Agent Skills Directory

[SAFE]: The instructions mandate the use of Pydantic and Zod for input validation, which effectively mitigates common injection vulnerabilities in the generated backend code.
[SAFE]: Security-centric rules require the implementation of JWT with refresh token rotation and bcrypt for password hashing, aligning with modern security standards.
[SAFE]: The skill explicitly forbids the agent from performing unauthorized package installations, directing it instead to document requirements for the user.
[SAFE]: All referenced code templates and snippets demonstrate secure coding practices, such as using parameterized queries and consistent authorization checks.

backend-agent