persona-hr-coordinator

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, suspicious code, or unauthorized data access attempts were detected. The skill instructions follow normal operational logic for an HR coordinator persona.
  • [PROMPT_INJECTION]: The skill processes external data from emails and shared documents, which introduces a surface for indirect prompt injection. 1. Ingestion points: Processes incoming emails via gws-gmail and documents via gws-drive. 2. Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present. 3. Capability inventory: The skill can send emails, post to Chat spaces, and create calendar events. 4. Sanitization: Recommends the use of a --sanitize flag for PII, but lacks specific sanitization for instructional content in processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 01:27 PM
Security Audit — agent-trust-hub — persona-hr-coordinator