goal-writer
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions focus on assisting the user with drafting and refining structured objectives. It mandates user approval before any goal is created and emphasizes the use of verification tests and clear scope boundaries.
- [PROMPT_INJECTION]: No evidence of prompt injection or attempts to bypass agent safety protocols was found. The instructions reinforce adherence to user intentions.
- [DATA_EXFILTRATION]: No network calls or commands for accessing sensitive local data are present.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any remote code execution, package installation, or unauthorized shell commands.
Audit Metadata