handoff
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a process for conversation summarization and handoff preparation using natural language instructions.
- [SAFE]: The instructions explicitly require the agent to redact sensitive information, such as API keys, passwords, and personally identifiable information (PII), which aligns with security best practices.
- [DATA_EXPOSURE]: The skill directs the agent to save the handoff document to the temporary directory of the user's operating system rather than the current workspace. This is a functional requirement for cross-session handoffs and does not involve automated exfiltration or unauthorized access.
- [PROMPT_INJECTION]: No patterns of prompt injection, jailbreaking, or instruction overrides were detected. The skill maintains standard agent interaction protocols.
Audit Metadata