agent-handoff-protocols
Fail
Audited by Snyk on May 16, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt serializes and injects full handoff context (including collected_data and conversation history) directly into agent system prompts and tickets, which can contain API keys or passwords and thus forces the LLM to receive and potentially output secrets verbatim.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata