clean-code
Warn
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses the YAML frontmatter field
priority: CRITICALto influence the agent's internal task prioritization and importance ranking. - [PROMPT_INJECTION]: The instructions use high-pressure and mandatory language (e.g., 'CRITICAL', 'MANDATORY', '🔴 VIOLATION') designed to override default agent behavior and ensure strict adherence to the author's workflow.
- [COMMAND_EXECUTION]: The 'Verification Scripts' section provides a mapping that mandates the execution of Python scripts via the shell (e.g.,
python ~/.Codex/skills/frontend-design/scripts/ux_audit.py .). These scripts reside in external directories outside the skill's control and are executed with agent permissions.
Audit Metadata