handoff
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a standard utility for session management and contains no evidence of malicious code, obfuscation, or unauthorized data exfiltration.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes conversation history for use by subsequent agents. This is an inherent risk of handoff tools and is considered low impact.
- Ingestion points: The conversation history from the active session.
- Boundary markers: No specific delimiters or markers are required for the output document.
- Capability inventory: The agent writes a summary file to the operating system's temporary directory.
- Sanitization: The instructions explicitly mandate the redaction of API keys, passwords, and personally identifiable information.
Audit Metadata