Splunk unknown stable spl

Ollama Excessive API Requests

Detects high Ollama API request volumes from a single client in a short time window. A burst may indicate automated abuse or contribute to resource contention, but GIN access logs do not establish malicious intent or service impact; validate the client and workload against local usage baselines.

View Source

Detection Logic

`ollama_server`
"[GIN]"
| rex field=_raw "\
| \s+(?<raw_status>\d+)\s+\
| \s+(?<raw_latency>[\d\.]+(?:µs
| ms
| s))\s+\
| \s+(?<raw_src>[^
| ]+?)\s+\
| \s+(?<raw_method>\w+)\s+\"(?<raw_path>[^\"]+)\""
| eval src=coalesce(src, trim(raw_src))
| eval uri_path=coalesce(uri_path, raw_path)
| eval http_method=coalesce(http_method, raw_method)
| eval http_response_code=coalesce(http_response_code, raw_status)
| eval response_time_ms=coalesce(response_time_ms, case(match(raw_latency, "µs$"), tonumber(replace(raw_latency, "µs", ""))/1000, match(raw_latency, "ms$"), tonumber(replace(raw_latency, "ms", "")), match(raw_latency, "s$"), tonumber(replace(raw_latency, "s", ""))*1000))
| where isnotnull(src)
| bin _time span=5m
| stats count as request_count
        dc(uri_path) as distinct_endpoints
        values(uri_path) as endpoints
  by _time src
| where request_count > 120
| eval severity="medium"
| eval attack_type="High Volume API Activity"
| `ollama_excessive_api_requests_filter`

False Positives

  • ⚠ Legitimate automated services (CI/CD pipelines, monitoring tools, batch jobs), multiple users behind NAT/proxy infrastructure, or authorized load testing activities may trigger this detection during normal operations. Operator must adjust threshold accordingly.

Field Validations

Loading…

Comments (0)

Loading comments...