interview-system-designer
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or unauthorized data access behaviors were detected during the analysis of the skill's instructions, metadata, and associated Python scripts.
- [COMMAND_EXECUTION]: The skill includes several Python utilities (
hiring_calibrator.py,loop_designer.py,question_bank_generator.py) designed for local command-line use. Analysis of these scripts shows they only use safe, standard library functions for processing JSON data and generating text/JSON outputs. - [EXTERNAL_DOWNLOADS]: The skill files and documentation explicitly state that no external dependencies are required. The scripts do not perform any remote package installations or fetch code from external URLs.
- [DATA_EXFILTRATION]: There are no network-enabled capabilities within the skill. Data processing is entirely local, and no instructions were found that attempt to send sensitive information to remote servers.
- [PROMPT_INJECTION]: The instructional content in SKILL.md and README.md follows standard documentation patterns and does not contain any attempts to override agent behavior, bypass safety guardrails, or extract system prompts.
Audit Metadata