Unusual High Word Policy Blocks Detected

ELASTIC detection rule by Elastic · Elastic License v2

Detects repeated compliance violation 'BLOCKED' actions coupled with specific policy name such as 'word_policy', indicating persistent misuse or attempts to probe the model's denied topics.

[metadata]
creation_date = "2024/11/20"
integration = ["aws_bedrock"]
maturity = "production"
updated_date = "2025/11/10"

[rule]
author = ["Elastic"]
description = """
Detects repeated compliance violation 'BLOCKED' actions coupled with specific policy name such as 'word_policy',
indicating persistent misuse or attempts to probe the model's denied topics.
"""
false_positives = ["New model deployments.", "Testing updates to compliance policies."]
from = "now-60m"
interval = "10m"
language = "esql"
license = "Elastic License v2"
name = "Unusual High Word Policy Blocks Detected"
note = """## Triage and analysis

### Investigating Unusual High Word Policy Blocks Detected

Amazon Bedrock Guardrail is a set of features within Amazon Bedrock designed to help businesses apply robust safety and privacy controls to their generative AI applications.

It enables users to set guidelines and filters that manage content quality, relevancy, and adherence to responsible AI practices.

Through Guardrail, organizations can define "word filters" to prevent the model from generating content on profanity, undesired subjects,
and they can establish thresholds for harmful content categories, including hate speech, violence, or offensive language.

#### Possible investigation steps

- Identify the user account whose prompts contained profanity and whether it should perform this kind of action.
- Investigate other alerts associated with the user account during the past 48 hours.
- Consider the time of day. If the user is a human (not a program or script), did the activity take place during a normal time of day?
- Examine the account's prompts and responses in the last 24 hours.
- If you suspect the account has been compromised, scope potentially compromised assets by tracking Amazon Bedrock model access, prompts generated, and responses to the prompts by the account in the last 24 hours.

### False positive analysis

- Verify the user account that queried denied topics, is not testing any new model deployments or updated compliance policies in Amazon Bedrock guardrails.

### Response and remediation

- Initiate the incident response process based on the outcome of the triage.
- Disable or limit the account during the investigation and response.
- Identify the possible impact of the incident and prioritize accordingly; the following actions can help you gain context:
    - Identify the account role in the cloud environment.
    - Identify if the attacker is moving laterally and compromising other Amazon Bedrock Services.
    - Identify any regulatory or legal ramifications related to this activity.
- Review the permissions assigned to the implicated user group or role behind these requests to ensure they are authorized and expected to access bedrock and ensure that the least privilege principle is being followed.
- Determine the initial vector abused by the attacker and take action to prevent reinfection via the same vector.
- Using the incident response data, update logging and audit policies to improve the mean time to detect (MTTD) and the mean time to respond (MTTR).
"""
references = [
    "https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-components.html",
    "https://atlas.mitre.org/techniques/AML.T0051",
    "https://atlas.mitre.org/techniques/AML.T0054",
    "https://www.elastic.co/security-labs/elastic-advances-llm-security",
]
risk_score = 47
rule_id = "3216949c-9300-4c53-b57a-221e364c6457"
setup = """## Setup

This rule requires that guardrails are configured in AWS Bedrock. For more information, see the AWS Bedrock documentation:

https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-create.html
"""
severity = "medium"
tags = [
    "Domain: LLM",
    "Data Source: AWS Bedrock",
    "Data Source: AWS S3",
    "Use Case: Policy Violation",
    "Mitre Atlas: T0051",
    "Mitre Atlas: T0054",
    "Resources: Investigation Guide",
]
timestamp_override = "event.ingested"
type = "esql"

query = '''
from logs-aws_bedrock.invocation-*

// Expand multivalued policy names
| mv_expand gen_ai.policy.name
| mv_expand gen_ai.policy.action

// Filter for blocked profanity-related policy violations
| where
  gen_ai.policy.action == "BLOCKED"
  and gen_ai.compliance.violation_detected == "true"
  and gen_ai.policy.name == "word_policy"

// keep relevant user field
| keep user.id

// count blocked profanity attempts per user
| stats
    Esql.ml_policy_blocked_profanity_count = count()
  by user.id

// Filter for excessive policy violations
| where Esql.ml_policy_blocked_profanity_count > 5

// sort by violation volume
| sort Esql.ml_policy_blocked_profanity_count desc
'''

[[ currentRule.title && currentRule.title.length > 60 ? currentRule.title.slice(0, 60) + '…' : currentRule.title ]]

69a0a978-f2d1-4ff2-93e5-3b702198e6b9

Propose edits, view related rules, and engage with the community through comments.

Executable code, not a declarative rule

This submission is arbitrary [[ currentRule.format ? currentRule.format.toUpperCase() : '' ]] code, not a declarative detection rule — review it as you would any script before running it, and note that it cannot be safely aggregated or auto-executed alongside YARA/Sigma/Suricata/CRS rules.

Rejected pattern present

[[ reason ]]

What does this mean?

Format & documentation suggestions

Not a security issue — this rule is valid and was accepted as-is. These are optional fields/conventions its own format recommends, mainly affecting its quality score and how well it documents itself for other reviewers.

[[ reason ]]

What do these messages mean?

[[ currentRule.title && currentRule.title.length > 60 ? currentRule.title.slice(0, 60) + '…' : currentRule.title ]]

[[ currentRule.title ]]

Community Discussion