resilience-hub-failure-mode-assessment

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

• Third-party content exposure detected (high risk: 0.75). At runtime, the workflow uses AWS CLI/MCP calls to retrieve failure-mode findings and full finding details (including free-text fields like name, description, and especially reasoning from get-failure-mode-finding), which are outsider-authored from AWS/Resilience Hub’s generated outputs and are fed into the agent’s LLM context when the skill “present[s] findings” and “present[s] AI-generated service functions” for review.