handoff
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a standard administrative function to facilitate session continuity. It directs the agent to summarize the conversation and reference existing artifacts rather than duplicating them.
- [INDIRECT_PROMPT_INJECTION]: The skill processes conversation history which represents an untrusted data ingestion surface. However, the instructions mitigate risk by explicitly requiring the redaction of sensitive information.
- Ingestion points: The current conversation history is used as the primary data source.
- Boundary markers: No specific delimiters are defined for the input history.
- Capability inventory: The skill utilizes file-writing capabilities to save a document to the system's temporary directory.
- Sanitization: The instructions include a mandatory redaction step for API keys, passwords, and PII.
Audit Metadata