handoff-prompt
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references architectural guidelines and documentation from well-known technology organizations, including Anthropic, OpenAI, Microsoft, and LangChain, concerning agent handoff patterns and context engineering.- [PROMPT_INJECTION]: The skill processes repository data and tool outputs to generate instructions for a successor agent. While this creates a potential surface for indirect prompt injection from project content, the risk is mitigated by explicit instructions to remove sensitive data and a requirement for the receiving agent to ground its actions in verifiable evidence.
Audit Metadata