onboard
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No attempts to override agent behavior or bypass safety filters were detected. The use of instructional terms like 'CRITICAL' and 'IMPORTANT' is focused on design best practices.
- [DATA_EXPOSURE]: The skill does not access sensitive files, environment variables, or hardcoded credentials. It does not perform any network operations.
- [EXTERNAL_DOWNLOADS]: The documentation mentions well-known frontend libraries (such as Tippy.js and React Joyride) as implementation suggestions, but does not include commands to download or install them.
- [COMMAND_EXECUTION]: There are no shell commands or subprocess calls present in the skill.
- [DYNAMIC_EXECUTION]: The skill includes a benign JavaScript snippet demonstrating the use of
localStoragefor tracking UI states. This is provided as an example for the user and is not executed by the agent. - [PERSISTENCE_MECHANISMS]: No attempts to establish persistence on the host system were identified.
Audit Metadata