Elastic medium stable kql
GCP Vertex AI Safety Filters Set to BLOCK_NONE
Detects Vertex AI GenerateContent requests that set safety_settings.threshold to BLOCK_NONE. That threshold disables category blocking for the listed harm categories when clients explicitly send safetySettings. Attackers and careless apps use BLOCK_NONE to weaken built-in Gemini filters.
Detection Logic
from logs-gcp_vertexai.prompt_response_logs-* metadata _id, _version, _index
| where
data_stream.dataset == "gcp_vertexai.prompt_response_logs" and
MV_CONTAINS(gcp.vertexai.prompt_response_logs.full_request.safety_settings.threshold, "BLOCK_NONE")
| keep
_id,
_version,
_index,
@timestamp,
cloud.project.id,
gcp.vertexai.prompt_response_logs.model,
gcp.vertexai.prompt_response_logs.api_method,
gcp.vertexai.prompt_response_logs.full_request.contents.parts.text,
gcp.vertexai.prompt_response_logs.full_request.safety_settings.category,
gcp.vertexai.prompt_response_logs.full_request.safety_settings.threshold,
gcp.vertexai.prompt_response_logs.full_response.candidates.finish_reason,
gcp.vertexai.prompt_response_logs.full_response.candidates.safety_ratings.category,
gcp.vertexai.prompt_response_logs.full_response.candidates.safety_ratings.probability False Positives
- ⚠ Approved research projects that document BLOCK_NONE for evaluation. Prefer labeled service accounts and exclude those principals.
Field Validations
Loading…
Comments (0)
Loading comments...