← Library
splApache-2.0from splunk/security_content

AWS Bedrock Claude excessive use of tokens

Detects identities generating anomalously large model responses relative to their own historical baseline. For each identity, computes the average, maximum, and standard deviation of output token counts across all invocations, then flags any identity whose single largest response exceeds two standard deviations above their own mean. A statistically significant output spike from a single identity may indicate bulk data extraction, successful prompt injection producing verbose output, or a runaway agentic loop hitting context limits.

Quality
67
FP risk
Forks
0
Views
0
Rule source🔒 locked
🔒

Sign in to view the rule source

Free accounts can view the source for the top-ranked rules. Create one in seconds — no credit card required.

Sign in →