handoff
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes the current conversation history to generate a handoff document, creating an attack surface for instructions embedded in the chat log.
- Ingestion points: The entire conversation history is processed to extract goals, state, and decisions.
- Boundary markers: The output is structured using a specific markdown template defined in the instructions.
- Capability inventory: The skill utilizes file system write capabilities to save the document in the operating system's temporary directory.
- Sanitization: The instructions explicitly require the redaction of secrets, including API keys, passwords, tokens, and personal data, which mitigates data exposure risks.
Audit Metadata