handoff
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes the conversation history as untrusted data to generate a summary.
- Ingestion points: Untrusted data enters the agent context via the current conversation history being summarized.
- Boundary markers: No explicit delimiters or boundary markers are defined for the processed conversation content.
- Capability inventory: The skill utilizes file system write capabilities to save the handoff document to the operating system's temporary directory.
- Sanitization: The instructions contain a strong negative constraint, directing the agent to redact sensitive information including API keys, passwords, and personally identifiable information before generating the file.
Audit Metadata