The Agent Skills Directory

Prompt Injection (SAFE): The skill uses natural instructional language to guide an interview process and does not attempt to override agent safety protocols or extract system instructions.
Data Exfiltration (SAFE): While the skill collects personal information (drivers, work habits, failures), it lacks any network-capable tools, such as curl or fetch, to transmit this data. The output is directed to a local file.
Remote Code Execution (SAFE): No executable scripts, package manager files (requirements.txt, package.json), or remote download patterns were identified in the provided files.

persona-interview