AWS Bedrock Claude Sensitive Data in Prompts: endpointWeb ApplicationNoneversion:1
This detection identifies sensitive data such as social security numbers, passwords, API keys, and credit card numbers being sent in prompts to AWS Bedrock Claude models. Exposure of sensitive data through AI prompts may indicate data loss, credential leakage, or insider threat activity.
AWS Bedrock Claude Hostile Prompt Sentiment: endpointWeb ApplicationNoneversion:1
This detection identifies prompts with hostile or aggressive sentiment being sent to AWS Bedrock Claude models. Hostile prompts may indicate potential abuse, harassment, or other malicious intent.
AWS Bedrock Claude Unusually Large Prompts: endpointWeb ApplicationNoneversion:2
This detection identifies unusually large prompts sent to AWS Bedrock Claude models by calculating the statistical baseline of input token counts and flagging requests that exceed one standard deviations above the mean. Abnormally large prompts may indicate prompt injection attacks, data exfiltration attempts, or abuse of the AI service.
AWS Bedrock Claude High Risk Filesystem and Exec Tool Invocation: endpointWeb ApplicationNoneversion:1
Detects identities invoking high-risk filesystem and execution tools via AWS Bedrock Claude. For each identity, monitors the usage of potentially dangerous commands and flags any anomalous activity that deviates from their historical baseline. This may indicate attempts to escalate privileges, exfiltrate data, or execute unauthorized commands.
AWS Bedrock Claude Possible Prompt Injection: endpointWeb ApplicationNoneversion:1
This search surfaces AWS Bedrock Claude prompts containing phrases commonly associated with prompt injection or jailbreak attempts, such as instruction overrides, persona switching, or requests to ignore prior guidance. These strings are not inherently malicious on their own - many of them (for example "act as", "you must", or "new persona") appear routinely in legitimate system prompts, few-shot examples, and role-play or creative-writing use cases. This is a hunting search rather than an anomaly detection because the base rate of benign matches is high; use it to pivot into the surrounding conversation and look for corroborating signals such as the phrase appearing mid-conversation rather than in an expected system/few-shot prompt, the user attempting to override guardrails or safety instructions rather than set a benign persona, instructions that follow the injected phrase requesting privilege escalation, data exfiltration, or access to restricted tools/resources, repeated or iterative attempts from the same user/role after being refused, and injected phrases originating from untrusted input (e.g., retrieved documents or tool output) rather than the human user turn.
AWS Bedrock Claude excessive use of tokens: endpointWeb ApplicationNoneversion:1
Detects identities generating anomalously large model responses relative to their own historical baseline. For each identity, computes the average, maximum, and standard deviation of output token counts across all invocations, then flags any identity whose single largest response exceeds two standard deviations above their own mean. A statistically significant output spike from a single identity may indicate bulk data extraction, successful prompt injection producing verbose output, or a runaway agentic loop hitting context limits.
AWS Bedrock Claude Cross Region Possible Inference Abuse: endpointWeb ApplicationNoneversion:1
This detection identifies potential cross-region inference abuse in AWS Bedrock Claude models. Cross-region inference abuse may indicate attempts to bypass regional restrictions, exfiltrate data, or perform unauthorized actions across different AWS regions.
