handoff
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes conversation history, creating a surface for indirect prompt injection where untrusted data is summarized and saved to a file.
- Ingestion points: Conversation history (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: File system write to OS temporary directory.
- Sanitization: Includes instructions to redact API keys, passwords, and PII.
Audit Metadata