handoff
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill creates a handoff document by summarizing the current conversation, which acts as a potential surface for indirect prompt injection if the conversation contains malicious instructions meant to influence the subsequent agent session.
- Ingestion points: The skill ingests the entire active conversation history to generate the summary (SKILL.md).
- Boundary markers: There are no explicit delimiters or instructions defined for the resulting handoff file to help the receiving agent distinguish between the summary and potentially malicious instructions embedded within it (SKILL.md).
- Capability inventory: The skill requires file system read and write capabilities to manage the handoff documents in the user's directory (SKILL.md).
- Sanitization: The instructions include a specific constraint to exclude "Class A" data, such as secrets, credentials, and PII, which mitigates data exposure but does not prevent instruction injection (SKILL.md).
Audit Metadata