The Agent Skills Directory

[SAFE]: No malicious patterns detected. The skill instructions focus on interviewing the user and exploring the codebase to answer questions about a plan or design.
[DATA_EXPOSURE]: The skill instructs the agent to explore the codebase if a question can be answered that way. This is standard behavior for developer-focused agents and no specific sensitive files or exfiltration paths are mentioned.
[PROMPT_INJECTION]: The use of the word 'relentlessly' is a persona instruction for the interview process and does not constitute a safety bypass or instruction override.

grill-me