handoff
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes the current conversation, which may contain untrusted data, to generate a handoff document for other agents.
- Ingestion points: The entire current conversation history is used as input for summarization.
- Boundary markers: The skill does not define specific delimiters for the summarized content, though it focuses on high-level summarization.
- Capability inventory: The skill performs a file-write operation to save the document to the operating system's temporary directory.
- Sanitization: The skill contains explicit instructions to identify and remove sensitive information, such as API keys, passwords, and personally identifiable information (PII), before saving the document.
Audit Metadata