skills/react/react/flags/Gen Agent Trust Hub

flags

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to run the yarn flags command, a project-specific utility. It uses the $ARGUMENTS variable to pass user-defined flags such as --diff, --cleanup, and --csv directly to the command line tool.
  • [PROMPT_INJECTION]: The skill processes user-supplied input through the $ARGUMENTS variable which is then interpolated into a shell command. While this defines an entry point for potential indirect prompt injection or command manipulation, the behavior is constrained to the specific yarn flags tool and is necessary for the skill's primary purpose of providing a flexible CLI interface for feature flag management.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 10:51 AM
Security Audit — agent-trust-hub — flags