handoff
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes the current conversation history as its primary input, creating a surface for indirect prompt injection if the conversation contains untrusted content.
- Ingestion points: Processes the user's current conversation history to generate a handoff document (SKILL.md).
- Boundary markers: The skill does not use explicit boundary markers to delimit untrusted content, but it does include instructions to redact sensitive data.
- Capability inventory: The skill's primary capability is writing a text summary to the operating system's temporary directory.
- Sanitization: Explicitly instructs the agent to redact API keys, passwords, and personally identifiable information (PII) before saving.
Audit Metadata