custom-agent-definitions

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a reference for creating custom agent definitions in the .claude/agents/ directory. It uses standard YAML frontmatter and Markdown bodies as defined in the provided schema.
  • [SAFE]: No remote code execution, external downloads, or network operations are present. All examples are localized to project configuration.
  • [SAFE]: The documentation explicitly promotes security best practices, such as the Principle of Least Privilege and using context: fork to isolate agent tasks.
  • [SAFE]: No obfuscation, prompt injection, or sensitive data exfiltration patterns were detected in the instructions or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:11 PM