Skills
skills/johnefemer/skillfish/interview-system-designer/Gen Agent Trust Hub

interview-system-designer

Fail

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: HIGHCOMMAND_EXECUTIONNO_CODEDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The SKILL.md file contains numerous instructions and examples for the agent to execute shell commands such as python loop_designer.py, python question_bank_generator.py, and python hiring_calibrator.py.
  • [NO_CODE]: The core functionality described in the skill depends on three Python scripts (loop_designer.py, question_bank_generator.py, and hiring_calibrator.py) that are missing from the skill directory. This makes the skill's behavior unverifiable and potentially dangerous if the agent is induced to create or download these scripts from untrusted sources.
  • [DATA_EXFILTRATION]: The hiring_calibrator.py script is designed to process interview_results.json, which contains sensitive demographic data including gender and ethnicity. Since the source code for the script is missing, it is impossible to verify whether this sensitive information is handled securely or exfiltrated to an external service.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 18, 2026, 04:18 PM
Security Audit — agent-trust-hub — interview-system-designer