The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation and architectural workflows. It contains no executable scripts, shell commands, or network operations.- [DATA_EXPOSURE]: Mentions of sensitive paths like secrets or credentials occur strictly within security guidance sections in 'references/production-quality.md', advising correct management practices such as using managed secret storage and keeping sensitive data out of logs.- [EXTERNAL_DOWNLOADS]: Includes informational links to official documentation from trusted sources such as Microsoft Azure, Google Cloud, AWS, NIST, and Martin Fowler. These are used for reference and do not trigger automated code execution or package installation.- [INDIRECT_PROMPT_INJECTION]: The skill provides a structured workflow for analyzing existing codebases. It includes explicit instructions to model trust boundaries and validate untrusted input, which are standard architectural practices that improve security posture against injection attacks.

software-architecture