handoff
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes the current conversation history to generate a handoff document, which creates an attack surface for instructions embedded in the chat to influence the agent's summary.
- Ingestion points: The skill reads the "current conversation" content as the primary data source for the handoff file (SKILL.md).
- Boundary markers: Absent. The instructions do not specify delimiters to separate the conversation content from the agent's summarization logic.
- Capability inventory: The skill utilizes file-writing capabilities to save markdown files into the
.handoffs/directory at the repository root. - Sanitization: The skill explicitly instructs the agent to redact sensitive information such as API keys, passwords, and PII before writing the output.
Audit Metadata