Akhilucky/AI-firewall
github analyzed 4570507 deep scan unknown
Multi-agent LLM security layer detecting prompt injection and jailbreaks.
Akhilucky/AI-firewall is an MCP server distributed on github, maintained by Akhilucky, tracked here since June 2026. It has shipped 0 releases and exposes 5 tools. Tools include analyze_prompt, benchmark_firewall, get_firewall_status, get_threat_breakdown, sanitize_prompt. Its composite risk grade is A — an inferred review prompt computed from observed signals, not a verdict.
tools
-
analyze_promptAnalyze a prompt for injection, jailbreaks, exfiltration, and leakage -
benchmark_firewallRun the adversarial test suite and return detection statistics -
get_firewall_statusHealth check: vector DB size, model status, uptime -
get_threat_breakdownDetailed per-signal scoring breakdown from the last analysis -
sanitize_promptClean a suspicious prompt while preserving legitimate content
release cadence · 90d
No releases yet.
recent releases
No releases yet.