write-goal
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is text transformation and task structuring. It does not interact with the file system, network, or external APIs, and contains no executable code.
- [PROMPT_INJECTION]: The instructions include a standard directive to ignore the skill's trigger name ('$write-goal') when extracting the user's task. This is a common parsing pattern for agent skills and does not represent a bypass of safety protocols.
- [DATA_EXFILTRATION]: No patterns involving sensitive file access, environment variable reading, or network transmission were detected.
Audit Metadata