aws-harness

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow is the agent invocation path where the operating user supplies prompt/input.prompt (user-controlled free text) that is fed into the model via agent(user_message) / agentcore invoke, which is outsider-authored content relative to the harness text.