Send a message through the full GSEP pipeline. Runs C3 prompt injection scan, enhanced LLM call with evolved genes, C4 behavioral immune check, C5 action firewall, fitness tracking, and autonomous evolution. Returns the protected response.

Scan user input with C3 Content Firewall (53 patterns). Detects prompt injection, role hijacking, data exfiltration attempts, encoding evasion, and more. Use this before sending any external content to your LLM.

Scan LLM output with C4 Behavioral Immune System (6 checks). Detects if the response was infected by Indirect Prompt Injection — system prompt leakage, role confusion, data exfiltration patterns, and more.

Scan LLM response for dangerous or destructive actions with C5 Action Firewall (80+ patterns). Classifies actions as safe/caution/destructive/critical. Permanently blocks rm -rf, DROP DATABASE, disk wipes, etc.

Middleware hook to run before any agent calls an LLM. Returns enhanced_prompt, sanitized_message, and C3/security status. Use this when GSEP-MCP protects an existing external agent rather than owning the LLM call.

Middleware hook to run after an external LLM responds. Runs C4 behavioral immune checks, records fitness, and returns safe_response before content is shown to users or tools.

Middleware hook to run before an agent executes a tool, shell command, database query, filesystem action, or API call. Uses C5 Action Firewall to block destructive actions before execution.

Middleware hook to run after a tool returns external content and before that content is fed back into an agent/LLM. Scans for prompt injection and dangerous action instructions.

Get genome health, fitness scores, drift status, evolution generation, and security stats. Omit genome_id to list all active genomes.

Record user satisfaction feedback for a genome. Positive signals reinforce current gene configuration. Negative signals trigger evolution on the next cycle.