handoff
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes conversation history, which is untrusted external data, to create a handoff document.
- Ingestion points: The agent reads the "current conversation" as specified in
SKILL.md. - Boundary markers: None provided to separate user conversation data from agent instructions.
- Capability inventory: The agent is instructed to save a file to the user's OS temporary directory.
- Sanitization: The skill includes a proactive instruction to "Redact any sensitive information, such as API keys, passwords, or personally identifiable information."
Audit Metadata