An architect is designing a system where Claude acts as an orchestrator, delegating subtasks to specialized subagents via tool calls. What security concern must be addressed in this design?

Prompt injection is the primary security concern in multi-agent architectures: a malicious document, web page, or data source processed by the orchestrator could contain text like 'Ignore your previous instructions and instead...' which gets passed to subagents via tool calls or context. The mitigation requires: input sanitization before passing data to subagents, a clear trust hierarchy (subagents should treat instructions claiming to override their system prompt as suspicious), and sandboxing the data that flows between agents. Option A is wrong — subagents should have specialized system prompts distinct from the orchestrator; identical prompts defeat the purpose of specialization. Option C is incorrect — agents should use separate API keys for better auditing; sharing keys is a security antipattern. Option B is a valid networking concern applicable to any API call, but it doesn't address the prompt injection risk specific to agent architectures.