handoff
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted conversation data to generate a handoff document containing instructions for a future agent session.
- Ingestion points: Conversation history and user-provided arguments are processed by the agent.
- Boundary markers: No explicit delimiters or boundary markers are specified to separate summarized conversation content from the instructions intended for the next agent.
- Capability inventory: The agent performs file write operations to the system temporary directory and instructs the subsequent agent to load specific skills.
- Sanitization: The instructions include a requirement to redact sensitive information such as API keys, passwords, and PII, mitigating potential data exposure.
Audit Metadata