aws-lambda-durable-functions

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

• Third-party content exposure detected (high risk: 0.78). The skill ingests outsider-authored free text via the troubleshooting workflow’s step that runs aws lambda get-durable-execution-history --include-execution-data, where the returned execution history “execution data may contain sensitive information,” which can include arbitrary external callback payloads and step results, and then the agent analyzes and verbatim-exposes parts of that data in its LLM context.