| CompositeDetector |
Composite injection detector that chains multiple InjectionDetector
implementations in priority order, short-circuiting on the first positive. |
| DetectionResult |
|
| LLMPromptGuardFilter |
Detects and blocks prompt-injection attacks
before they reach the downstream LLM API.
|
| LLMPromptGuardFilter.Heaplet |
|
| LLMProxyFilter |
Identity-aware LLM proxy filter.
|
| LLMProxyFilter.Heaplet |
|
| MCPServerFeaturesFilter |
MCPServerFeaturesFilter
This filter enforces allow/deny policies for MCP (Management & Control Protocol)
features exchanged as JSON-RPC payloads with an MCP server.
|
| MCPServerFeaturesFilter.Heaplet |
|
| RegexDetector |
Layer-1 injection detector: deterministic, sub-millisecond regex matching.
|
| RegexDetector.PatternEntry |
Raw pattern entry before compilation (maps to injection-patterns.json).
|
| TokenRateLimiter |
Identity-aware, in-memory token-bucket rate limiter for LLM prompt tokens.
|
| TypoglycemiaDetector |
Layer-2 Injection detector: catches prompt-injection keywords that have been
typoglycemia-obfuscated — i.e. their interior letters are scrambled
while the first and last characters are preserved.
|