handoff
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for conversational summarization and state handoff between agent sessions.
- [SAFE]: It contains specific safety instructions to redact sensitive information such as API keys and passwords before saving, demonstrating security-aware design.
- [SAFE]: The skill processes the current conversation and user arguments, which acts as a source of untrusted data (Indirect Prompt Injection surface). Ingestion points: conversation history and user arguments in SKILL.md. Boundary markers: Absent. Capability inventory: Writing to OS temporary directory. Sanitization: Redaction of secrets and PII. This surface is considered safe given the intended purpose and redaction controls.
- [SAFE]: File system activity is restricted to the OS temporary directory for transient storage.
Audit Metadata