interview-coach

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • Prompt Injection (SAFE): No malicious instruction overrides or bypass attempts were found. The skill uses role-playing constraints (e.g., 'Do NOT break character') which are standard for its intended use case.
  • Data Exposure & Exfiltration (SAFE): No hardcoded credentials, sensitive file path access, or unauthorized network operations were identified.
  • Unverifiable Dependencies & Remote Code Execution (SAFE): The skill does not include any external package manifests (requirements.txt, package.json) or remote script execution patterns.
  • Obfuscation (SAFE): No Base64, zero-width characters, or other encoding-based obfuscation techniques were detected in the prompt or reference files.
  • Indirect Prompt Injection (SAFE): While the skill processes user input (interview answers), it lacks exploitable capabilities such as file writing, command execution, or network access, rendering the risk of downstream exploitation negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 09:04 PM