The Agent Skills Directory

[DATA_EXPOSURE_&_EXFILTRATION]: The skill processes potentially sensitive data (resumes and employment history) but does not include any network operation tools (like curl, wget, or requests) or commands to write data to external locations.
[SAFE]: The helper script scripts/_common.py includes predefined regex patterns for detecting personally identifiable information (PII) such as email addresses, Japanese phone numbers, and 'MyNumber' identifiers. This facilitates data safety by allowing the agent to identify and protect sensitive user information.
[COMMAND_EXECUTION]: The skill invokes a local Python script scripts/find_probe_points.py. Analysis of this script confirms it is deterministic, processing input JSON data into preparation points without spawning subshells or executing arbitrary commands.
[SAFE]: The instructions in SKILL.md explicitly prohibit the agent from taking autonomous actions such as contacting recruiters, scheduling interviews, or faking experience, ensuring the agent remains within a safe operational boundary.
[OBFUSCATION]: No instances of Base64 encoding, zero-width characters, homoglyphs, or other obfuscation techniques were detected in the instructions or scripts.

interview-prep