career-junior-onboarding

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, command executions, or sensitive file access were detected. The skill functions solely as a text-based career coach.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential ingestion surface by advising the processing of external data such as payslips and labor contracts (ingestion point: SKILL.md). However, it defines a clear boundary by requiring a PII masking process (boundary marker: related skills section) to sanitize sensitive data (sanitization: references/kr-pii-masking.md) and lacks high-privilege capabilities such as network operations or file writing (capability inventory: none).
  • [SAFE]: All referenced skills and modules (e.g., moai-career, moai-coworker, moai-writer) are verified vendor resources belonging to the skill author's ecosystem (modu-ai/moai) and represent normal functional dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 01:42 PM
Security Audit — agent-trust-hub — career-junior-onboarding