handoff
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to summarize the current conversation into a handoff document for a fresh agent. This creates a surface where malicious instructions in the chat history could be carried over into the summary and influence the behavior of the agent that consumes the handoff.
- Ingestion points: The skill processes the current conversation history, which includes untrusted user input.
- Boundary markers: The instructions do not specify using delimiters or 'ignore' instructions in the resulting handoff file to prevent the next agent from misinterpreting the summary content as new instructions.
- Capability inventory: The skill requires file system write access to save the handoff document (e.g., in a
.handoff/folder). - Sanitization: While the skill explicitly instructs the agent to redact sensitive information like API keys and PII, it lacks instructions to sanitize or escape executable prompt patterns within the generated summary.
Audit Metadata