The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for a conversational interview workflow. It does not include any executable scripts, binary files, or external dependencies.
[SAFE]: No network operations, file system modifications, or sensitive data access patterns were detected. The workflow is restricted to text-based interaction with the user.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user input (interview answers), it lacks the capabilities (such as shell execution, file writing, or network requests) that could be exploited via indirect injection. The instructions define clear boundary markers for conversation flow, which helps maintain context.
[SAFE]: The configuration file agents/openai.yaml only enables implicit invocation, which is a standard platform setting and does not introduce security vulnerabilities in this context.

interview-me