setup-claude-code

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [DATA_EXPOSURE]: The skill accesses the user's home directory path ~/.claude/agents/ to inspect existing global agent configurations. This check is performed to notify the user if project-level agents will override existing user-level settings.
  • [COMMAND_EXECUTION]: The skill prepares configurations for sub-agents (builder and checker) that are granted Bash, Write, and Edit capabilities. These agents are instructed to dynamically identify and execute build or test commands found within the project's configuration files, such as package.json.
  • [PROMPT_INJECTION]: The loop-go command template utilizes the $ARGUMENTS placeholder to pass user-supplied task descriptions directly into the builder agent's instructions. This is a standard mechanism for parameterizing agent tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 11:10 AM
Security Audit — agent-trust-hub — setup-claude-code