Detection: AWS Bedrock Claude excessive use of tokens

Updated Date: 2026-07-06 ID: a839a6f7-aaac-438b-9d99-be0b49481e17 Author: Rod Soto Type: Anomaly Product: Splunk Enterprise Security

Description

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.

Search

 1`aws_bedrock_claude`
 2
 3| spath output="out_tokens" path="output.outputBodyJson.usage.output_tokens"
 4
 5| eval user = replace('identity.arn', ".*/", "")
 6
 7| stats count           AS invocations,
 8        avg(out_tokens) AS avg_out,
 9        max(out_tokens) AS max_out,
10        stdev(out_tokens) AS stdev_out
11  BY user, identity.arn
12
13| eval stdev_out  = coalesce(stdev_out, 0)
14
15| eval threshold  = avg_out + (2 * stdev_out)
16
17| where max_out > threshold
18
19| table
20    user,
21    identity.arn,
22    invocations,
23    avg_out,
24    max_out,
25    stdev_out,
26    threshold
27
28| sort -max_out
29
30| `aws_bedrock_claude_excessive_use_of_tokens_filter`

Data Source

Name	Platform	Sourcetype	Source
AWS Bedrock Claude	AWS	`'json_no_timestamp'`	`'aws_bedrock'`

Macros Used

Name	Value
aws_bedrock_claude	`(sourcetype="json_no_timestamp")`
aws_bedrock_claude_excessive_use_of_tokens_filter	`search *`

aws_bedrock_claude_excessive_use_of_tokens_filter is an empty macro by default. It allows the user to filter out any results (false positives) without editing the SPL.

Annotations

- MITRE ATT&CK

+ Kill Chain Phases

+ NIST

+ CIS

- Threat Actors

ID	Technique	Tactic
T1055	Process Injection	Privilege Escalation

Exploitation

DE.AE

CIS 10

Default Configuration

This detection is configured by default in Splunk Enterprise Security to run with the following settings:

Setting	Value
Disabled	true
Cron Schedule	`0 * * * *`
Earliest Time	`-70m@m`
Latest Time	`-10m@m`
Schedule Window	`auto`
Creates Finding (Notable)	No
Creates Intermediate Finding (Risk Event)	Yes

Anomaly detections generate Intermediate Findings (Risk Events). They do not generate a Finding (Notable) directly.

Implementation

You must install and configure the Splunk Add-on for AWS (https://splunkbase.splunk.com/app/1876). Enable Amazon Bedrock model invocation logging in AWS so that Claude request/response payloads are delivered to S3 and/or CloudWatch Logs (see https://docs.aws.amazon.com/bedrock/latest/userguide/model-invocation-logging.html for setup steps), then ingest those logs into Splunk via the AWS TA. Configure the aws_bedrock_claude macro to point to the index and sourcetype (json_no_timestamp) where these logs land.

Known False Positives

This detection may produce false positives for identities with low invocation history, legitimate large document summarization tasks, or automated pipeline sessions with naturally variable output token counts.

Associated Analytic Story

Suspicious AWS Bedrock Claude Activities

Intermediate Findings

Message	Entity Field	Entity Type	Risk Score
Identity $user$ generated anomalously high output tokens in AWS Bedrock Claude with max output $max_out$ above threshold $threshold$.	user	user	20

References

Detection Testing

Test Type	Status	Dataset	Source	Sourcetype
Validation	✅ Passing	N/A	N/A	N/A
Unit	✅ Passing	Dataset	`http:bulkawsbedrock`	`json_no_timestamp`
Integration	✅ Passing	Dataset	`http:bulkawsbedrock`	`json_no_timestamp`

Replay any dataset to Splunk Enterprise by using our replay.py tool or the UI. Alternatively you can replay a dataset into a Splunk Attack Range

Source: GitHub |

Version: 1