onboard
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
clayCLI tool to perform actions such asclay whoami,clay onboard options, andclay onboard select. These commands are used to check the user's onboarding status and retrieve configuration data from the vendor's services. - [INDIRECT_PROMPT_INJECTION]: The skill processes data (labels, descriptions, and instructions) fetched dynamically from the
clayCLI. This data is used to present options to the user and guide the agent's next steps. - Ingestion points: Output from
clay onboard optionsandclay onboard selectinSKILL.md. - Boundary markers: None identified; instructions are followed as if provided directly by the user.
- Capability inventory: The skill has access to the
BashandReadtools, enabling file access and shell command execution. - Sanitization: No explicit sanitization or validation of the fetched instructions is described.
- [DYNAMIC_EXECUTION]: The skill dynamically follows natural language instructions returned by the
clay onboard selectcommand to perform specific tasks. This behavior is tied to the skill's primary purpose of providing an interactive onboarding experience.
Audit Metadata