chief-people

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill defines a highly structured operational environment using specific templates (ORG-XXXX, HIRE-XXXX, etc.) and human approval gates, minimizing the risk of autonomous malicious behavior.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it processes and organizes untrusted data into strategic documents.
  • Ingestion points: Data for job descriptions, organizational structures, and performance reviews provided in the user context or associated files.
  • Boundary markers: The skill uses structured Markdown templates but lacks explicit instructions to ignore embedded instructions within processed data.
  • Capability inventory: Limited to writing structured documents to the .agile-v/business/ directory; no network, shell, or remote execution capabilities are present.
  • Sanitization: No specific input sanitization or validation routines are defined for the personnel and organizational data processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 06:07 AM
Security Audit — agent-trust-hub — chief-people