claude-handoff
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill constructs and executes a command using the
claudeCLI tool to launch background processes. It interpolates a generated summary and a descriptive name into the command string (claude --bg --name "<name>" "<summary>"). This is a legitimate use of the platform's tooling for session management. - [DATA_EXPOSURE]: The skill contains a safety directive requiring the agent to redact sensitive information, such as API keys, passwords, and personally identifiable information (PII), from the conversation summary before it is passed to the next session.
Audit Metadata