hreng-hire-eval

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • Prompt Injection (LOW): The skill is susceptible to indirect prompt injection because it processes untrusted candidate submissions as primary input. A candidate could potentially include hidden instructions within their code or notes to bias the AI's scoring.\n
  • Ingestion points: Candidate submission files and interview notes (identified in SKILL.md).\n
  • Boundary markers: None present; instructions do not explicitly tell the agent to ignore instructions embedded within candidate data.\n
  • Capability inventory: The skill utilizes local scripts for output validation but lacks high-privilege capabilities like network access.\n
  • Sanitization: No input sanitization or validation of the candidate's content is performed before processing.\n- Command Execution (SAFE): The skill contains a shell script (scripts/check-hreng-hire-eval.sh) and a Python script (scripts/validate-hreng-hire-eval.py) for verifying the format of evaluation reports. These scripts are executed locally and do not perform any unauthorized or malicious operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 10:05 PM