The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using the Bash tool to run tests, manage package dependencies, and open local coverage reports. These commands are standard for the intended development and testing workflow.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and execute code from the project's test files, which constitutes a standard attack surface for development-oriented agents. Ingestion points: Reads project files including package.json and various test files via the Read tool. Boundary markers: None explicitly defined in the prompts. Capability inventory: Includes Bash execution and file writing. Sanitization: Relies on the host Bun runtime's isolation capabilities.
[SAFE]: No evidence of data exfiltration, credential theft, obfuscation, or persistence mechanisms was found. The skill's operations are transparent and aligned with its stated purpose.

bun-test