skills/yennanliu/ai_experiment/hr/Gen Agent Trust Hub

hr

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to process external, potentially untrusted documents.
  • Ingestion points: The skill workflow involves using Read and Grep tools to review existing employee handbooks and HR policies (SKILL.md).
  • Boundary markers: There are no instructions or delimiters provided to help the agent distinguish between its own instructions and content found within read files.
  • Capability inventory: The agent is authorized to use Read, Write, Edit, Grep, and Bash for file system operations (SKILL.md).
  • Sanitization: No sanitization or content validation steps are included for the data retrieved from external documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 02:36 PM