create-subagent

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands such as git rev-parse, mkdir, and ln -s. These operations are used to manage the local repository structure and are consistent with the skill's stated purpose of scaffolding files.
  • [PROMPT_INJECTION]: The skill constructs an AGENTS.md file by interpolating user-provided text into a template. This represents an indirect injection surface if the generated content is later used to define agent behavior without further review.
  • Ingestion points: User input captured by the script scripts/gather-subagent-info.cjs via terminal prompts.
  • Boundary markers: None; the gathered text is placed directly into markdown headers and workflow sections.
  • Capability inventory: Local file system management, directory scaffolding, and symlink creation.
  • Sanitization: Minimal; basic string trimming is performed on input values.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 04:09 PM
Security Audit — agent-trust-hub — create-subagent