The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directs the agent to execute local shell commands including bun run build, uv run lintro chk, grep, and ls. These commands are used to validate the project's build state and verify the presence of required theme assets and configurations.
[DATA_EXFILTRATION]: There are no indicators of data exfiltration. The skill does not perform network requests or attempt to access sensitive files outside of the project directory (e.g., .ssh or .env files).
[PROMPT_INJECTION]: No prompt injection patterns were found. The instructions are focused on checking implementation details and do not attempt to bypass safety filters or override agent behavior.
[EXTERNAL_DOWNLOADS]: The skill does not download or execute scripts from external or untrusted remote sources.

turbo-verify