explain

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute system utilities including tokei, ast-grep, rg, and fd. User-provided inputs for the target argument are used within these shell commands (e.g., test -f "$TARGET", tokei "$TARGET"). This relies on the agent's internal safety controls to prevent command injection via the target string if malicious arguments are provided.- [PROMPT_INJECTION]: The skill exhibits an Indirect Prompt Injection surface because it retrieves and processes content from the local codebase to provide explanations to a sub-agent.
  • Ingestion points: Local files and directory contents read via the Read tool or Bash commands (e.g., bat or cat equivalents).
  • Boundary markers: Absent. The skill does not define specific delimiters or instructions to ignore embedded prompts in the analyzed files when routing to expert agents.
  • Capability inventory: File system access (Read, Glob, Bash), shell command execution (Bash), and agent delegation (Task tool).
  • Sanitization: Absent. Content from files is passed to sub-agents for analysis without filtering or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 11:30 AM