using-groundwork

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill employs high-pressure language to override the agent's natural decision-making regarding tool use.
  • It uses directive markers such as "EXTREMELY-IMPORTANT", "ABSOLUTELY MUST", and "not negotiable" to force specific behaviors.
  • The instructions explicitly command the agent to disregard its own reasoning or "rationalization" when deciding whether to invoke a tool, which is a behavioral override technique.
  • [NO_CODE]: The skill consists entirely of markdown instructions and a DOT diagram for workflow visualization.
  • No executable scripts, shell commands, or external dependencies are included in the file.
  • [SAFE]: The primary purpose of the skill is to enforce a structured operational workflow within the agent's environment, utilizing the platform's intended 'Skill' tool capability.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 09:41 PM