{"description":"Trending threats, MITRE ATT\u0026CK coverage, and detection metadata. Fed continuously.","feed_url":"https://feed.craftedsignal.io/products/amazon-claude-models/feed.json","home_page_url":"https://feed.craftedsignal.io/","items":[{"_cs_actors":[],"_cs_cpes":[],"_cs_cves":[],"_cs_exploited":false,"_cs_has_poc":false,"_cs_poc_references":[],"_cs_products":["Amazon Bedrock","Amazon Claude Models"],"_cs_severities":["medium"],"_cs_tags":["cloud-security","aws","ai-security","prompt-injection","data-exfiltration","anomaly-detection"],"_cs_type":"advisory","_cs_vendors":["Amazon Web Services"],"content_html":"\u003cp\u003eThis brief details a detection engineering approach to identify suspicious activity within AWS Bedrock Claude models. The focus is on flagging unusually large prompts, which are anomalous input token counts that significantly exceed a statistical baseline. This method aims to uncover potential prompt injection attacks where adversaries attempt to manipulate the AI model's behavior, data exfiltration attempts where large volumes of sensitive information might be queried or extracted, or general abuse of the AI service resources. The detection calculates the statistical average and standard deviation of \u003ccode\u003einput.inputTokenCount\u003c/code\u003e and flags requests that are one standard deviation above the mean and exceed a minimum threshold of 1000 input tokens, requiring defenders to monitor their AI interactions for these specific behavioral deviations.\u003c/p\u003e\n\u003ch2 id=\"impact\"\u003eImpact\u003c/h2\u003e\n\u003cp\u003eSuccessful prompt injection attacks can lead to unauthorized data access, manipulation of AI model outputs, or compromise of sensitive information by coercing the model to reveal internal configurations or bypass safety mechanisms. Data exfiltration attempts via large prompts could lead to the exposure of confidential company data or intellectual property. Abuse of AI services might result in significant unexpected costs due to excessive token usage, resource exhaustion, or even reputational damage if the AI is misused for malicious purposes. The consequences include financial losses, regulatory non-compliance, and loss of user trust.\u003c/p\u003e\n\u003ch2 id=\"recommendation\"\u003eRecommendation\u003c/h2\u003e\n\u003cul\u003e\n\u003cli\u003eEnable Amazon Bedrock model invocation logging to ensure Claude request/response payloads are delivered to S3 and/or CloudWatch Logs, as detailed in the AWS documentation \u003ccode\u003ehttps://docs.aws.amazon.com/bedrock/latest/userguide/model-invocation-logging.html\u003c/code\u003e.\u003c/li\u003e\n\u003cli\u003eDeploy the Sigma rule included in this brief to your SIEM, configuring log ingestion from AWS Bedrock services to allow correlation with \u003ccode\u003einput.inputTokenCount\u003c/code\u003e fields.\u003c/li\u003e\n\u003cli\u003eInstall and configure the Splunk Add-on for AWS from \u003ccode\u003ehttps://splunkbase.splunk.com/app/1876\u003c/code\u003e and ingest relevant AWS Bedrock logs for advanced statistical analysis.\u003c/li\u003e\n\u003cli\u003eReview alerts generated by the \u003ccode\u003einput.inputTokenCount\u003c/code\u003e detection to differentiate legitimate large queries from potential prompt injection or data exfiltration attempts.\u003c/li\u003e\n\u003c/ul\u003e\n","date_modified":"2026-07-16T10:30:43Z","date_published":"2026-07-16T10:30:43Z","id":"https://feed.craftedsignal.io/briefs/2026-07-aws-bedrock-large-prompts/","summary":"This brief outlines a detection strategy for identifying unusually large prompts sent to AWS Bedrock Claude models, which may indicate prompt injection attacks, data exfiltration attempts, or abuse of the AI service, warranting investigation by detection engineers.","title":"Detecting Unusually Large Prompts to AWS Bedrock Claude Models","url":"https://feed.craftedsignal.io/briefs/2026-07-aws-bedrock-large-prompts/"}],"language":"en","title":"CraftedSignal Threat Feed - Amazon Claude Models","version":"https://jsonfeed.org/version/1.1"}