The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and YAML templates. It contains no executable scripts, binaries, or automated command execution logic.
[CREDENTIALS_UNSAFE]: The skill follows security best practices by explicitly instructing users never to store secrets in Git. It describes the platform's mechanism for injecting database credentials via environment variables at runtime, which is a secure standard.
[DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were detected. Network references in the templates (e.g., Microsoft Graph, external host examples) are standard placeholders used for defining legitimate application access policies.
[PROMPT_INJECTION]: The instructions are purely functional and do not attempt to override agent safety guidelines, bypass system constraints, or extract system prompts.

nais-manifest