The Agent Skills Directory

[SAFE]: The skill instructions and associated templates are focused on standard MoonBit development tasks. No indicators of prompt injection, data exfiltration, or obfuscation were found.
[COMMAND_EXECUTION]: The skill employs standard MoonBit CLI commands such as moon new, moon check, and moon test. These are legitimate tools for the language and are used according to their intended purpose within the development workflow.
[INDIRECT_PROMPT_INJECTION]: The skill takes user requirements as input to generate API scaffolds. While this provides a surface for indirect prompt injection, the risk is minimized as the output is restricted to standard code templates and is validated by language tools like moon check.

moonbit-spec-test-development