interview-system-designer

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted JSON data from external files which could be used to influence the agent's decision-making or behavior.
  • Ingestion points: The tools hiring_calibrator.py, loop_designer.py, and question_bank_generator.py all ingest external data via the --input argument, including candidate details and role definitions.
  • Boundary markers: The scripts do not implement specific boundary markers or instructions to the agent to ignore potentially malicious instructions embedded within the input data.
  • Capability inventory: The skill has the ability to write files to the local system and generates complex reports that are interpreted by the agent to provide hiring recommendations.
  • Sanitization: While the tools perform basic JSON structure validation and numeric range checks, they do not sanitize natural language content that could be interpolated into prompts in subsequent agent steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 08:06 AM
Security Audit — agent-trust-hub — interview-system-designer