agent-command-authoring

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill instructions. The content is purely educational and focuses on best practices for command delegation.
  • [COMMAND_EXECUTION]: The skill suggests using the ls command to verify the presence of subagent files in configuration directories such as ~/.claude/agents/ and ~/.config/opencode/agents/. This is a benign, read-only diagnostic operation used for workflow validation.
  • [SAFE]: The skill defines a structured format for creating local configuration files. These files act as thin wrappers for internal agent tasks and do not introduce external dependencies or execution of untrusted code.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 06:04 PM