handoff
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows security best practices by explicitly instructing the agent to redact sensitive information including API keys, passwords, and personally identifiable information (PII) before generating the handoff document.
- [COMMAND_EXECUTION]: The skill instructions involve writing a document to the system's temporary directory. This is a standard operation for creating persistent session handoffs and is restricted to the user's local environment with specific redaction requirements to ensure data privacy.
- [PROMPT_INJECTION]: The skill processes user conversation history to create a summary. While this creates a surface for indirect prompt injection, the instructions emphasize content redaction and referencing external artifacts by link rather than duplication, which mitigates the risk of inheriting malicious instructions into the agent's context.
Audit Metadata