The Agent Skills Directory

[SAFE]: The skill serves as an informational resource for backend architecture and does not include any scripts, commands, or hidden instructions that pose a risk.
[DATA_EXFILTRATION]: The skill explicitly promotes secure handling of sensitive data by recommending managed secrets governance services like Infisical and avoiding the use of environment files in production.
[PROMPT_INJECTION]: The skill instructs the agent to treat all external inputs, including tool outputs and project documentation, as untrusted boundaries that require explicit validation and audit, effectively mitigating potential indirect prompt injection attacks.

backend-architect