agents-subagents

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill content is purely instructional and provides templates for subagent configuration using YAML frontmatter.
  • [SAFE]: The instructions explicitly advocate for security-oriented principles, including least-privilege tool selection, safety rails for destructive actions, and context budgeting to avoid sensitive data exposure.
  • [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized remote code execution was found.
  • [SAFE]: All referenced file paths and internal links are consistent with the structure of an AI agent skill and do not point to sensitive system areas.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 04:22 AM