The Agent Skills Directory

[SAFE]: The skill does not contain any malicious patterns, obfuscation, unauthorized network access, or credential harvesting.- [DATA_EXPOSURE]: The skill includes a step to save an interview summary to docs/ito-temp/idea/[topic].md. This is a standard file system operation within a project scope and requires explicit user confirmation before execution.- [PROMPT_INJECTION]: The skill is designed to process untrusted user input as part of its core functionality (the questioning loop). While this creates a surface for Indirect Prompt Injection if a user provides instructions disguised as answers, the risk is limited as the agent is instructed to control the summary format and the output is stored locally.

ito-grill