The Agent Skills Directory

[NO_CODE]: The skill contains only instructional Markdown and YAML frontmatter. It does not include any executable scripts, binaries, or automated command-edge triggers.
[SAFE]: The instructions are focused on guiding an AI agent through a diagnostic workflow (checking configuration sync, rule quality, and test coverage). No malicious patterns such as prompt injection, unauthorized data access, or network exfiltration were detected.
[COMMAND_EXECUTION]: While the skill mentions the nao CLI (e.g., nao sync), it does so in the context of checking if the user has previously run these commands, rather than attempting to execute arbitrary or dangerous shell commands itself.
[DATA_EXPOSURE]: The skill instructs the agent to read internal documentation (RULES.md, nao_config.yaml) and test results. This is consistent with its stated purpose of auditing the local environment and does not involve accessing sensitive system files like SSH keys or cloud credentials.

audit-context