Unusual High Word Policy Blocks Detected

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.

Detection logic

Its licence does not clear it for publishing here

Sunturai publishes a detection's own text where the licence it arrived under has been reviewed and permits it, and Elastic License 2.0 has not. The query as its source wrote it, its canonical form and the hash that pins this revision are in the workspace record.

Known benign triggers

New model deployments.
Testing updates to compliance policies.

References

Links the source published beside this detection. Reference is the link the source wrote, unmodified. Class is decided by this catalogue from the host and path, not stated by the source. Cited by counts published detections citing the same resource, including this one, and the sources beneath it count the repositories this catalogue ingests, which is not the same as independent research.
Reference	Class	Cited by
atlas.mitre.org/techniques/AML.T0051	Unclassified	8
atlas.mitre.org/techniques/AML.T0054	Unclassified	7
docs.aws.amazon.com/bedrock/latest/userguide/guardrails-components.html	Product documentation	8
www.elastic.co/security-labs/elastic-advances-llm-security	Threat report	21

Detection rules

Unusual High Word Policy Blocks Detected

Detection logic

Known benign triggers

MITRE ATT&CK mappings

References

From the source

Licence

Authorship

Detection rules