AWS Bedrock Model Invocation Abnormal Token Usage

Status: Experimental
Severity: informational
Log types: AWS.BedrockModelInvocation
Tags: AWS, Bedrock, Resource Hijacking
Reference: https://stratus-red-team.cloud/attack-techniques/AWS/aws.impact.bedrock-invoke-model/
Source: github.com/panther-labs/panther-analysis

Monitors for potential misuse or abuse of AWS Bedrock AI models by detecting abnormal token usage patterns and alerts when the total token usage exceeds the appropriate threshold for each different type of model.

MITRE ATT&CK coverage

Tactic	Techniques
Impact	`T1496.004` Resource Hijacking: Cloud Service Hijacking

Rule body yaml

AnalysisType: rule
Filename: aws_bedrockmodelinvocation_abnormaltokenusage.py
RuleID: "AWS.BedrockModelInvocation.AbnormalTokenUsage"
DisplayName: "AWS Bedrock Model Invocation Abnormal Token Usage"
Enabled: true
LogTypes:
    - AWS.BedrockModelInvocation
Tags:
    - AWS
    - Bedrock
    - Resource Hijacking
Status: Experimental
Severity: Info
Reports:
    MITRE ATT&CK:
        - TA0040:T1496.004
Description: Monitors for potential misuse or abuse of AWS Bedrock AI models by detecting abnormal token usage patterns and alerts when the total token usage exceeds the appropriate threshold for each different type of model.
Runbook: Verify the alert details by checking token usage, model ID, and account information to confirm unusual activity, examine user access patterns to identify potential credential compromise, and look for evidence of prompt injection, unusual repetition, or attempts to bypass usage limits. Apply stricter usage quotas to the affected account, block suspicious IP addresses, and enhance the guardrails that are in place.
DedupPeriodMinutes: 60
Threshold: 1
Reference: https://stratus-red-team.cloud/attack-techniques/AWS/aws.impact.bedrock-invoke-model/
SummaryAttributes:
  - p_any_aws_account_ids
  - p_any_aws_arns
InlineFilters:
    - All: []
Tests:
    - Name: Converse Operation Unusual Token Patterns
      ExpectedResult: true
      Log:
        accountId: "111111111111"
        identity:
            arn: arn:aws:sts::111111111111:assumed-role/role_details/suspicious.user
        input:
            inputBodyJson:
                messages:
                    - content:
                        - text: I have a very suspicious question.
                      role: user
            inputContentType: application/json
            inputTokenCount: 0
        modelId: anthropic.claude-3-haiku-20240307-v1:0
        operation: Converse
        output:
            outputBodyJson:
                metrics:
                    latencyMs: 249
                output:
                    message:
                        content:
                            - text: You shouldn't ask this question
                        role: assistant
                usage:
                    inputTokens: 0
                    outputTokens: 0
                    totalTokens: 2000
            outputContentType: application/json
            outputTokenCount: 0
        region: us-west-2
        requestId: bb98d9a8-bd9a-47ca-976b-f165ef1f8b67
        schemaType: ModelInvocationLog
        schemaVersion: "1.0"
        timestamp: "2025-05-15 14:17:22.000000000"
    - Name: Converse Operation with Abnormal Token Usage
      ExpectedResult: true
      Log:
        accountId: "111111111111"
        identity:
            arn: arn:aws:sts::111111111111:assumed-role/role_details/suspicious.user
        input:
            inputBodyJson:
                messages:
                    - content:
                        - text: I have a very suspicious question.
                      role: user
            inputContentType: application/json
            inputTokenCount: 0
        modelId: anthropic.claude-3-haiku-20240307-v1:0
        operation: Converse
        output:
            outputBodyJson:
                metrics:
                    latencyMs: 249
                output:
                    message:
                        content:
                            - text: You shouldn't ask this question
                        role: assistant
                usage:
                    inputTokens: 0
                    outputTokens: 0
                    totalTokens: 5000
            outputContentType: application/json
            outputTokenCount: 0
        region: us-west-2
        requestId: bb98d9a8-bd9a-47ca-976b-f165ef1f8b67
        schemaType: ModelInvocationLog
        schemaVersion: "1.0"
        timestamp: "2025-05-15 14:17:22.000000000"
    - Name: Perform Another Operation
      ExpectedResult: false
      Log:
        accountId: "111111111111"
        identity:
            arn: arn:aws:sts::111111111111:assumed-role/role_details/regular.user
        input:
            inputBodyJson:
                messages:
                    - content:
                        - text: I have a rather normal question.
                      role: user
            inputContentType: application/json
            inputTokenCount: 0
        modelId: anthropic.claude-3-haiku-20240307-v1:0
        operation: ListModels
        output:
            outputBodyJson:
                metrics:
                    latencyMs: 249
                output:
                    message:
                        content:
                            - text: I can respond to this question
                        role: assistant
                usage:
                    inputTokens: 0
                    outputTokens: 0
                    totalTokens: 0
            outputContentType: application/json
            outputTokenCount: 0
        region: us-west-2
        requestId: bb98d9a8-bd9a-47ca-976b-f165ef1f8b67
        schemaType: ModelInvocationLog
        schemaVersion: "1.0"
        timestamp: "2025-05-15 14:17:22.000000000"
    - Name: Regular Converse Operation with Normal Token Usage
      ExpectedResult: false
      Log:
        accountId: "111111111111"
        identity:
            arn: arn:aws:sts::111111111111:assumed-role/role_details/regular.user
        input:
            inputBodyJson:
                messages:
                    - content:
                        - text: I have a rather normal question.
                      role: user
            inputContentType: application/json
            inputTokenCount: 0
        modelId: anthropic.claude-3-haiku-20240307-v1:0
        operation: Converse
        output:
            outputBodyJson:
                metrics:
                    latencyMs: 249
                output:
                    message:
                        content:
                            - text: I can respond to this question
                        role: assistant
                usage:
                    inputTokens: 0
                    outputTokens: 0
                    totalTokens: 0
            outputContentType: application/json
            outputTokenCount: 0
        region: us-west-2
        requestId: bb98d9a8-bd9a-47ca-976b-f165ef1f8b67
        schemaType: ModelInvocationLog
        schemaVersion: "1.0"
        timestamp: "2025-05-15 14:17:22.000000000"

Detection logic

Condition

operation in ["InvokeModel", "Converse"]
output.outputBodyJson.usage.totalTokens gt "1000"
output.outputBodyJson.usage.outputTokens eq "0"

This rule also runs imperative logic the parser cannot express as a filter; the conditions above are the structured part it could extract.

Indicators

Each row is a field, operator, and value that the rule matches. The corpus column counts how many other rules in the catalog look for the same combination: high numbers point to widely-used, community-vetted indicators. Blank or 1 shows that the indicator is specific to this rule.

Field	Kind	Values
`operation`	in	`Converse` `InvokeModel`
`output.outputBodyJson.usage.outputTokens`	eq	`0`
`output.outputBodyJson.usage.totalTokens`	gt	`1000`

`j` / `k`	Scroll down / up
`d` / `u`	Half-page down / up
`gg` / `G`	Top / bottom
`h` / `l`	History back / forward
`f`	Follow link (`Shift` = new tab)
`/`	Focus search
`?`	Toggle this help
`↑` / `↓`	Navigate search results
`Enter`	Open highlighted result
`Esc`	Close results / dialog

`type:`	`events` / `rules` / `providers`
`vendor:`	`sigma` / `elastic` / `splunk` / `kusto` / `chronicle` (vendor name alone also works: `sigma:`, `kql:`, `secops:`…)
`tactic:`	TA-id, slug, or name: `credential_access`, `TA0006`
`technique:`	technique or sub-technique ID: `T1003`, `T1003.001` (alias `tech:`)
`severity:`	`critical` / `high` / `medium` / `low` / `informational` (alias `sev:`)
`risk_score`	Numeric comparison on the Elastic risk score (0 to 100): `risk_score>50`, `risk_score<=20`, `risk_score=99` (alias `risk`; Elastic rules only)
`stages:`	Rules with exactly N pipeline stages
`correlation:`	`single_event` / `sequence` / `alternatives` / `alternatives_cross_log` / `all_required` / `correlated`
`with:`	Co-occurrence event-id; stacks (`with:4624 with:4769`) to require all, while a comma list in one occurrence (`with:4624,4769`) is an either-or group. Implies multi-event
`like:`	Structural neighbors of a rule slug (equivalents + subsumption stricter / broader): `like:comsvcs_lsass_memory_dump-splunk-sysmon`
`groupby:`	Entity-grouping substring match against `group_by_keys`: `groupby:user`, `groupby:host`
`uses:`	Rules whose predicate tree touches the field (any kind, any value): `uses:CommandLine`
`excludes:`	Rules with top-level `not()` clauses on the field (FP whitelists): `excludes:ParentImage`
`field:` / `value:`	Predicate search; narrows rule cards to those with a matching leaf and drives the indicator tier. Unquoted = substring, wildcards allowed (`value:mimikatz`)
`indicator:`	Shorthand for `field:F value:V`: `indicator:Image=*\powershell.exe`
`kind:`	Filter by predicate kind. Narrows rule cards to those carrying a matching predicate leaf (`vendor:elastic kind:cidr_match`) and drives the indicator tier: `contains` / `starts_with` / `ends_with` / `regex` / `cidr` / `eq` / `in` … (operator aliases `op:`/`match:`)
`has:` / `no:`	`sample`, `field`, `notes`, `refs`, `trace`, `thirdparty`, `rule`, `pattern`, `timewindow`, `threshold`, `newterms`, `sigma`/`elastic`/`splunk`/`kusto`/`chronicle`
`-op:val`	Exclude matches; works on most operators but not `type:`/`like:`/`has:`/`no:` (use `no:<flag>` to exclude a rule flag): `tactic:execution -vendor:splunk`. Standalone `-kind:`/`-field:`/`-value:` drop every rule carrying a matching predicate leaf (`type:rules -kind:is_null`)
`field:"…"` / `value:"…"`	Quoted value = anchored exact match (also allows spaces): `value:"net user"`
`a,b`	Comma = OR inside one operator (`vendor:sigma,elastic`, `severity:high,critical`); repeating a facet merges the same way. `field:`/`value:` never split (literal commas)
`vendors:` / `stage:`	Singular and plural spellings fold to the canonical operator and value: `tactics:` = `tactic:`, `type:event` = `type:events`, `correlation:sequences` = `correlation:sequence`, `has:thresholds` = `has:threshold`
`"quoted phrase"`	Exact-match a multi-word phrase (free text)