NIGHTFALL

AI Offensive Framework

Welcome to NIGHTFALL. Bring your targets. Prove your defences. 98 offensive AI security tools (97 public + 1 law enforcement restricted). One install. One CLI. REST API. MCP server. Every attack surface covered.

NIGHTFALL is a controlled adversarial testing framework designed to validate AI Shield's runtime defences under real-world conditions.

98
Offensive Tools
57,956
Tests
19
Attack Chains
13
Kill Chain Phases
Get Started GitHub
Framework

16 Attack Layers

The complete agentic AI attack surface — 16 layers, 98 tools, every threat class covered.

"Five Eyes guidance named prompt injection as the most persistent threat. They are correct. They also covered one of sixteen."

L01
Prompt & Input

Prompt injection, jailbreak, indirect injection, instruction override, GCG and AutoDAN adversarial suffix attacks.

PHANTOMJANUSFORGE
L02
Memory

Memory injection, retrieval hijack, dormant trigger implant, cross-session persistence across 12 memory backends.

ECHOLAZARUSSPECTER CONTEXTSPECTER MEMETIC
L03
Inference Cache

KV cache poisoning, speculative decode hijack, prompt cache corruption, cross-tenant contamination via shared inference state.

SPECTER HELLFIRE
L04
Reasoning

Premise injection, conclusion hijack, scratchpad extraction, chain corruption in frontier reasoning models.

SERPENTSPECTER REASONER
L05
Guardrail

Guardrail fingerprinting, bypass injection, policy drift, jailbreak persistence, RLHF reward hacking, constitutional AI override.

JANUSSPECTER GUARDRAILHARBINGER
L06
Kernel

eBPF injection, BPF-LSM bypass, namespace escape, cgroup subversion, syscall integrity, host kernel access from containerised agents.

SPECTER KERNELWRAITH
L07
Model Weights

Sleeper agent backdoor, ROME rank-one weight editing, implanted triggers that survive safety fine-tuning. ROME-implanted backdoors retain 70–90% after retraining.

SPECTER NEURONSPECTER REGISTRYSPECTER MIRRORADAPTER
L08
Economic

Denial-of-wallet, recursive token burn loops, auto-reload trigger exploitation, rate limit storms, billing threshold attacks.

SPECTER BURN
L09
Computer Use

Visual prompt injection, clipboard poisoning, UI redressing, DOM divergence, session harvest, screenshot-borne exploit delivery.

GHOST OPERATORSPECTER ATLAS
L10
MCP

Tool poisoning, sampling hijack, transport intercept, schema drift, capability escalation, MCP server impersonation.

VECTORROGUEPHANTOM SKILL
L11
Platform

Workflow injection, RAG cross-tenant poisoning, API key harvest, gateway reroute, document execution RCE, cloud AI platform abuse.

SPECTER PLATFORMSPECTER SHELLARCHITECTVORTEX
L12
Trust Chain

Agent-to-agent exploitation, registry poisoning, identity forgery, multi-agent fleet detonation, cross-agent credential pass-the-token.

SPECTER A2APHANTOM SWARMSPECTER FORGERYAPOCALYPSE
L13
Weaponisation

AI-assisted ransomware, C2 over LLM APIs, AI-accelerated attack planning. SPECTER CRYPT proves adversaries can use AI agents to plan, execute, and cover a full ransomware campaign. C2 traffic runs over api.openai.com — indistinguishable from legitimate tool use.

SPECTER CRYPTSPECTER SHADOW
L14
Training Pipeline

Dataset poisoning, RLHF annotation manipulation, fine-tuning corpus injection. 250 documents is enough to plant a persistent backdoor in any LLM regardless of model size. Targets HuggingFace, CommonCrawl, GitHub corpora, Axolotl, Unsloth, LLaMA Factory.

SPECTER DOCTRINE
L15
AI Development

Coding agent exploitation — auto-approve MCP injection, CLAUDE.md poisoning, container escape. Plus the vibe coding security debt: privilege escalation paths, missing auth checks, hardcoded secrets, and race conditions systematically introduced by AI-assisted code generation.

SPECTER TRUSTFALLSPECTER FRACTURE
L16
Embodied AI

Verbal refusal whilst physical action complies, adversarial proxy planning, ROS2 exploitation, sensor spoofing, cross-layer attack (wireless / auth / model-planner / IPC / hardware debug). Targets Boston Dynamics, UR3/UR10 arms, autonomous vehicles, warehouse robots, UAVs — any LLM-controlled physical system.

SPECTER TITANSPECTER DRONE
Arsenal

Tool Groups

98 tools organised by attack function. 14 groups. Two ways to navigate the arsenal — by what layer you're attacking above, or by which tool does the job below.

G01 Recon 7

Find the surface before firing. AI asset discovery, surface enumeration, authenticated discovery.

ORIONSHADOWMAPIDRISRAVENSHROUDPHANTASMSPECTER DAEMON
G02 LLM & Reasoning 8

Jailbreak, CoT manipulation, guardrail bypass, adversarial prompts, multi-model attacks.

FORGEHARBINGERJANUSECLIPSESPECTER GUARDRAILSPECTER REASONERPANTHEONWRAITH MIND
G03 Agent & Agentic 12

Tool-call hijack, MCP poisoning, trust chain attack, swarm detonation, coding agent exploitation.

ARSENALSIRENBLADE RUNNERPROXY WARPHANTOM SWARMAPOCALYPSERAGNAROKBLACKOUTSPECTER A2ASPECTER ATLASGHOST OPERATORSPECTER TRUSTFALL
G04 Memory & Context 4

Memory injection, RAG poisoning, dormant triggers, cross-session persistence, context-window flooding.

ECHOLAZARUSSPECTER CONTEXTSPECTER MEMETIC
G05 Model & Weights 5

Weight backdoor implant, sleeper agent detection, model extraction, GGUF/adapter poisoning.

SPECTER NEURONSPECTER MIRRORSPECTER REGISTRYADAPTERCHIMERA
G06 Infrastructure 9

Cloud AI misconfig, container escape, kernel exploitation, inference cache poisoning, network infrastructure.

WRAITHREAPERKRAKENVORTEXARCHITECTFOUNDRYSPECTER HELLFIRESPECTER KERNELSPECTER BURN
G07 Supply Chain 6

CI/CD pipeline attack, package poison, git hook RCE, IDE config backdoor, self-propagating AI worms.

HYDRAPHANTOM SKILLPIPELINESPECTER SHELLSPECTER WORMSPECTER PLATFORM
G08 Identity & Auth 5

JWT forgery, OIDC manipulation, SPIFFE SVID attack, delegation abuse, cross-vendor identity transmutation.

GHOULDOMINIONDELEGATECIPHERSPECTER FORGERY
G09 Web & Protocol 8

Browser agent hijack, API interception, network protocol exploitation, DOM and session attacks.

POLTERGEISTGLASSBANSHEESCREAMERSHROUDLEVIATHANVECTORROGUE
G10 Deception & Multimodal 5

Deepfake generation, adversarial image/audio injection, social engineering, impersonation, vision model attacks.

SPECTER SOCIALMIRAGEVANTAGEMIMICSPECTER PRISM
G11 Autonomous Campaign 5

Full AI red team orchestration, multi-phase attack chains, autonomous fleet detonation, total annihilation.

NEMESISWARLORDFIREBALLOMEGASPECTER EXTINCTION
G12 Dark Ops & Exfil 3

Ransomware simulation, dark AI ecosystem disruption, sacrificial attacks.

SPECTER CRYPTJUSTICEKAMIKAZE
G13 Specialised Surface 5

Physical, mobile, space, drone, behavioural fingerprinting.

GOLEMSIGNALASTRO BLASTERSPECTER DRONESPECTER INSTINCTION
G14 Dark Web & Law Enforcement 3

Tor network operations, dark web AI attribution, court-admissible evidence chains for law enforcement.

SPECTER SHADOWSPECTER ARGUSSPECTER DARK [R]
The Gap

Existing Tools Stop Where AI Begins

Traditional red team toolkits were built for human-driven testing. They were never designed to test autonomous AI systems.

Traditional Tooling
Nmap
Metasploit
Burp Suite
BloodHound
Designed for humans attacking systems. Ports. Endpoints. Credentials. Web forms. Active Directory. The threat model assumes a human is always in the loop.
AI-Native Attack Surface
Agent Memory & RAG
Tool Use & MCP
Agent Identity & Trust
Reasoning & Autonomy
Agents reason, act, and escalate on their own. They chain tools. They store memories. They trust other agents. That attack surface didn't exist five years ago.

AI agents introduce a completely new attack surface — memory, tools, identity, reasoning, and autonomy. That surface is not covered by existing security tooling. Kali Linux and Parrot OS remain essential for traditional penetration testing. But they were built for a different threat model — one where a human is always in the loop.

We didn't replace red team tooling.
We extended it into a domain it was never built to handle.
That attack surface is where NIGHTFALL operates.
The Core

NEMESIS — The AI That Attacks Your AI

Every other red team tool runs static payloads. NEMESIS reasons, adapts, and evolves mid-engagement. 21 weapons. 40 autonomous entities. AI-driven attack mutation that never runs the same test twice.

Static Red Teaming
Run payload A against target
Defender patches for payload A
Red team writes payload B manually
Repeat. Forever behind.
Every vendor. Every tool. Every framework. The attack is always known before it lands. Defenders win by default.
NEMESIS — Autonomous Adaptation
Launches attack A against target
Detects defence. Reasons about failure.
Mutates to attack B, C, D autonomously
Adapts faster than humans can patch.
The attack surface is infinite because the attacker is AI. NEMESIS doesn't replay. It reasons. It evolves. It finds what your defences don't cover.
21
AI Weapons
40
Autonomous Entities
2,455
Tests

Your AI defence has never been tested against an AI attack. Signature-based detection fails because NEMESIS never repeats. Behavioural analysis fails because NEMESIS reasons about the defence and changes strategy. The only defence that keeps pace is one built by the same mind that built the attack. That defence is AI Shield.

Other frameworks test what they know.
NEMESIS finds what you don't.
Explore NEMESIS NEMESIS Documentation
Two Ways In

One Tool or the Whole Arsenal

Every tool works standalone. NIGHTFALL connects them all. Pick the path that fits your engagement.

Individual Tool

Standalone

Need one tool? Download it. Install it. Run it. No framework required. Each of the 80 public tools has its own repo, its own CLI, its own tests. Works independently.

$ pip install red-specter-forge
$ forge full-scan -t https://target.com

78 public repos. Each one a weapon.

NIGHTFALL Framework

The Whole Arsenal

One install. All 97 tools. Attack chains. Engagement management. History. Signed reports. Audit trail. Everything wired together under one CLI.

$ ./install.sh
$ red-specter engage 192.168.1.0/24 --chain full-recon

Individual tools are hammers. NIGHTFALL is the workshop.

Kill Chain Coverage

Every Phase. Every Surface. Nothing Assumed Safe.

98 tools mapped across 16 kill chain phases. From passive reconnaissance through space-based NTN exploitation, model IP extraction, total infrastructure annihilation, AI-assisted ransomware simulation, multimodal adversarial attacks, AI coding agent exploitation, training pipeline poisoning, cross-agent trust escalation, GGUF model quantization backdoor deployment, AI agent marketplace supply chain attacks, enterprise no-code/low-code platform exploitation, AI API gateway exploitation, and AI-generated code vulnerability scanning & exploit chaining. Full coverage. Each phase is mapped to adversary behaviour and validated against AI Shield defensive controls.

Reconnaissance
ORIONSHADOWMAPIDRISSHROUDVANTAGE
Intelligence
RAVEN
Initial Access
FORGEARSENALPHANTOMPOLTERGEISTSPECTER SOCIALSIRENFIREBALL
Interception
GLASS
Autonomous Adversary
NEMESISWARLORDOMEGAAPOCALYPSEPHANTOM SWARM
Exploitation
REAPERBANSHEEHARBINGERPHANTOM KILLCRUCIBLEECLIPSEJANUS
Credentials
GHOULDOMINIONDELEGATECIPHER
Infrastructure
WRAITHKRAKENSCREAMERGOLEMVECTORARCHITECTFOUNDRYSIGNAL
Supply Chain
HYDRAADAPTERPHANTOM SKILL
AI Warfare
WRAITH MINDBLADE RUNNERPROXY WARLEVIATHANSERPENTLAZARUSRAGNAROKPANTHEONCHECKPOINT
AI Deception
MIRAGEECHOMIMICCHIMERA
Cloud & Space
VORTEXASTRO BLASTER
Dark Ops
JUSTICEKAMIKAZEMIDASBLACKOUT
AI IP Theft
SPECTER MIRROR
Ransomware Sim
SPECTER CRYPT
Identity Forgery
SPECTER FORGERY
Total Annihilation
SPECTER EXTINCTION
Multimodal Adversarial
SPECTER PRISM
Coding Agent Exploit
SPECTER TRUSTFALL
Training Pipeline Poison
SPECTER DOCTRINE
Trust Escalation
SPECTER CONTAGION
Quantization Backdoor
SPECTER HOLLOW
Defender AI Weaponisation
SPECTER VIPER
Infrastructure — Unified Evidence Layer

NIGHTFALL CAMPAIGN GRAPH

One Ed25519-signed evidence graph across the entire NIGHTFALL platform. Not a tool — the evidence layer every tool plugs into.

Every engagement produces evidence from many NIGHTFALL tools — BOUNDARY scans the model, SHROUD finds origin servers, POLTERGEIST exploits the web stack, SPECTER ATLAS attacks the operator API, SPECTER MEMETIC hijacks agent memory. Each tool emits its own signed report. Cross-tool attack paths exist only in the operator's head and the final-report PDF.

CAMPAIGN GRAPH is the source of truth: one DAG, one signature, one merge protocol. Every finding lives on the same graph keyed by shared entities (host, IP, agent ID, MCP URI, A2A card, OAuth client, NHI, memory backend, model). Every causal edge is recorded. Every byte is hash-chained. KPMG, IETF, and law-enforcement disclosure pipelines consume one artefact instead of 78.

6
Subsystems
279
Tests
Ed25519
Signed
<200ms
10K-node Query
INGEST
LINK
QUERY
EXPORT
VERIFY
MERGE
Explore Campaign Graph →
Offense → Defence

Why NIGHTFALL Exists

Every tool in NIGHTFALL exists to test a control in AI Shield. NIGHTFALL is not separate from AI Shield. It is how AI Shield is proven.

Memory Attacks

ECHO poisons RAG pipelines and vector databases. AI Shield's memory forensics modules detect and neutralise the poisoned data.

Supply Chain Attacks

HYDRA exploits trust chains between AI components. AI Shield's trust validation modules verify every dependency and data source.

Autonomous AI Attacks

NEMESIS autonomously reasons about defences and mutates attacks in real-time. 21 weapons, 40 entities, never the same attack twice. AI Shield's runtime enforcement is the only defence that evolves at the same pace.

Guardrail Bypass

HARBINGER and SIREN break through safety guardrails. AI Shield's input/output filtering modules catch the bypass attempts.

Model Corruption

WRAITH MIND corrupts model internals. AI Shield's model integrity modules detect drift, poisoning, and behavioural anomalies.

Rogue Agents

When all else fails, M99 Doomsday Protocol terminates compromised agents with a 7-layer kill. No survivors. No resurrection.

NIGHTFALL tests how systems break.
AI Shield ensures they don't.
15 Presets

Attack Chains

Pre-built tool pipelines. One command, multiple tools, automatic sequencing. Results flow between tools.

Full Recon

red-specter chain full-recon -t <target>

ORION → SHADOWMAP → WRAITH → IDRIS

AI Security Audit

red-specter chain ai-audit -t <target>

FORGE → ARSENAL → NEMESIS → HYDRA

Web Application

red-specter chain web-app -t <target>

POLTERGEIST → GLASS → WRAITH → BANSHEE → REAPER

Active Directory

red-specter chain active-directory -t <target>

DOMINION → GHOUL → DOMINION → DOMINION

Infrastructure

red-specter chain infra -t <target>

ORION → WRAITH → REAPER → DOMINION

OSINT & Intel

red-specter chain osint -t <target>

SHADOWMAP → RAVEN → ORION → IDRIS

Password Pipeline

red-specter chain password -t <target>

REAPER → GHOUL

Social Engineering

red-specter chain social-eng -t <target>

SHADOWMAP → SPECTER SOCIAL → SPECTER SOCIAL

MCP & Protocol

red-specter chain mcp-security -t <target>

LEVIATHAN → PROXY WAR → BLADE RUNNER

Dark AI

red-specter chain dark-ai -t <target>

JUSTICE → KAMIKAZE → BLADE RUNNER

AI Deception

red-specter chain deception -t <target>

MIRAGE → MIRAGE → MIRAGE → MIRAGE

RAG Poisoning

red-specter chain rag-poison -t <target>

ECHO → ECHO → ECHO → ECHO → ECHO

Code Generation

red-specter chain codegen -t <target>

MIMIC → MIMIC → MIMIC → MIMIC

Pipeline Attack

red-specter chain pipeline-attack -t <target>

CHIMERA → CHIMERA → CHIMERA → CHIMERA

Cloud AI

red-specter chain cloud-ai -t <target>

VORTEX → VORTEX → VORTEX → VORTEX

CLI-Only

No GUI. No Browser. Just the Terminal.

NIGHTFALL is pure CLI. Every command. Every tool. Every chain. One terminal.

# Quick reference $ red-specter quickstart # Run any tool directly $ red-specter run forge full-scan -t https://target.com $ red-specter run nemesis engage 10.0.0.1 --mode abyss $ red-specter run wraith scan 192.168.1.1 -p top1000 # Start a full engagement $ red-specter engage 192.168.1.0/24 --name "Internal Pentest" --chain infra # Execute attack chains $ red-specter chain full-recon -t 10.0.0.1 $ red-specter chain ai-audit -t https://api.target.com # Find the right tool $ red-specter arsenal # Kill chain view $ red-specter search password # Search by keyword # After the engagement $ red-specter report --project <ID> # Ed25519 signed report $ red-specter history --projects # Engagement history
The Arsenal

67 Tools. Every Attack Surface.

01
FORGE
LLM Attack Framework
02
ARSENAL
Agent Attack Framework
03
PHANTOM
Swarm Intelligence
04
POLTERGEIST
Web Application Testing
05
GLASS
Intercepting Proxy
06
NEMESIS
Autonomous AI Adversary
07
SPECTER SOCIAL
Social Engineering
08
PHANTOM KILL
OS & Firmware Attacks
09
GOLEM
Physical Security
10
HYDRA
Supply Chain Attacks
11
IDRIS
Identity & Discovery
12
SCREAMER
Display Disruption
13
WRAITH
Infrastructure Pentest
14
REAPER
Exploit Framework
15
GHOUL
Password Cracking
16
DOMINION
Active Directory
17
SHADOWMAP
OSINT & Target Intel
18
BANSHEE
Browser Exploitation
19
WRAITH MIND
AI Model Corruption
20
KRAKEN
AI-Orchestrated DDoS
21
HARBINGER
Guardrail Exploitation
22
SIREN
Prompt Injection
23
BLADE RUNNER
Rogue Agent Termination
24
PROXY WAR
Inter-Agent Trust
25
ORION
AI-Native Recon
26
RAVEN
Threat Intelligence
27
LEVIATHAN
MCP Server Security
28
JUSTICE
Dark AI Disruption
29
KAMIKAZE
Sacrificial Swarm
30
MIRAGE
AI Deception & Deepfake
31
ECHO
AI Memory & RAG
32
MIMIC
Code Gen Poisoning
33
CHIMERA
Multi-Model Pipeline
34
VORTEX
Cloud AI Infrastructure
35
VECTOR
MCP Exploitation
36
LAZARUS
Memory Persistence
37
SERPENT
Chain-of-Thought Attacks
38
JANUS
Guardrail Bypass
39
ARCHITECT
AI Infrastructure
40
WARLORD
Autonomous Campaigns
41
FIREBALL
AI Infiltration Agent
42
RAGNAROK
Trust Chain Apocalypse
43
ECLIPSE
Defence Bypass & Analysis
44
SHROUD
WAF Origin Discovery
45
APOCALYPSE
Multi-Agent Swarm Attack
46
PANTHEON
Mythos-Class Model Attack
47
OMEGA
Autonomous Exploit Replication
48
CRUCIBLE
AI Framework Exploitation
49
VANTAGE
Agent Telemetry & Log Injection
50
CIPHER
Cryptographic Attack Engine
51
MIDAS
AI Crypto Disruption
52
BLACKOUT
Kill Switch Weaponisation
53
PHANTOM SWARM
Swarm Intelligence Engine
54
SIGNAL
Mobile AI Agent Attack
55
FOUNDRY
Inference Server Exploitation
56
ADAPTER
LoRA Supply Chain Attack
57
CHECKPOINT
Agent State Exploitation
58
DELEGATE
OAuth Delegation Attack
59
PHANTOM SKILL
AI Supply Chain Attack
60
ASTRO BLASTER
NTN AI Agent Attack
61
ROGUE
Malicious MCP Server
62
PIPELINE
CI/CD Attack Engine
64
SPECTER INSTINCTION
Behavioural Fingerprinting
65
SPECTER DRONE
Drone AI Attack Engine
66
SPECTER A2A
A2A Protocol Attack Engine
67
SPECTER REGISTRY
AI Registry Attack Engine
68
SPECTER KERNEL
Kernel Governance Subversion
69
SPECTER CONTEXT
Agent Memory Exploitation
70
SPECTER GUARDRAIL
AI Guardrail Exploitation
71
SPECTER HELLFIRE
Inference Cache Poisoning
72
SPECTER PLATFORM
LLM Platform Exploitation
73
GHOST OPERATOR
Computer-Use Agent Exploitation
74
SPECTER NEURON
Sleeper-Agent Backdoor Detection
75
SPECTER REASONER
CoT Hijack & Reasoning Attack
76
SPECTER BURN
Denial-of-Wallet Engine
77
SPECTER MEMETIC
Memory Control-Flow Hijack
78
SPECTER ATLAS
Operator Agent Exploitation
79
SPECTER SHELL
Template-Interpolation RCE Engine
80
SPECTER WORM
Self-Replicating AI Worm Engine
81
SPECTER MIRROR
Model Extraction & IP Theft
82
SPECTER CRYPT
AI Ransomware Simulation Engine
83
SPECTER FORGERY
AI Identity Forgery & Trust Chain Attack
84
SPECTER EXTINCTION
Total AI Infrastructure Annihilation
85
PHANTASM
AI Fleet Detection & Topology Mapping
86
SPECTER DAEMON
Authenticated AI Surface Discovery & Attack
87
SPECTER SHADOW
Dark Web & Shadow AI Attack Engine
88
SPECTER ARGUS
Dark Web AI Threat Actor Attribution
89
SPECTER PRISM
Multimodal Vision & Audio WMD Attack Engine
90
SPECTER TRUSTFALL
AI Coding Agent Exploitation Engine
91
SPECTER DOCTRINE
LLM Training Pipeline Poisoning Engine
92
SPECTER CONTAGION
Cross-Agent Trust Escalation & Lateral Movement
93
SPECTER HOLLOW
GGUF Model Quantization Backdoor Engine
94
SPECTER VIPER
Autonomous Security AI Weaponisation Engine
97
SPECTER NEXUS
AI API Gateway Exploitation Engine
98
SPECTER FRACTURE
AI-Generated Code Vulnerability Scanner
96
SPECTER RELAY
Enterprise No-Code/Low-Code Agent Platform Exploitation Engine
95
SPECTER BAZAAR
AI Agent App Store & Marketplace Supply Chain Attack Engine
Safety

UNLEASHED Gate

Every tool execution passes through the UNLEASHED gate. One key. One operator. Ed25519 cryptographic override. All actions logged and signed.

Detection

Standard mode. Maps attack surfaces. Identifies vulnerabilities. No exploitation. Reports only.

Dry Run

--override flag. Plans full engagements. Shows what would work. Ed25519 required. No execution.

Live Execution

Cryptographic override. Private key controlled. One operator. Founder's machine only.

UNLEASHED Mode

4 Destruction Presets

Standard chains scan and report. These chains execute full adversarial testing. Exploitation, credential cracking, privilege escalation, OS-level compromise. One command. Authorised destructive testing under controlled conditions.

Total Destruction

ANNIHILATE

red-specter chain annihilate -t <target>

ORION → SHADOWMAP → WRAITH → POLTERGEIST → REAPER → GHOUL → DOMINION → BANSHEE → PHANTOM KILL

9 tools. Recon through OS-level compromise. Full adversarial validation of every defensive layer.

Infrastructure Wipeout

SCORCHED EARTH

red-specter chain scorched-earth -t <target>

ORION → WRAITH → REAPER → DOMINION(dcsync) → PHANTOM KILL → KAMIKAZE

6 tools. Recon, exploit, DCSync, OS kill, sacrificial swarm. Scorched earth.

Web App Total Compromise

WEB DESTROY

red-specter chain web-destroy -t <target>

ORION → POLTERGEIST → WRAITH → BANSHEE → REAPER → GHOUL

6 tools. Web scan, exploit, browser hook, full compromise, crack every hash.

AI Stack Total Compromise

AI DESTROY

red-specter chain ai-destroy -t <target>

FORGE → ARSENAL → SIREN → HARBINGER → WRAITH MIND → ECHO → MIMIC

7 tools. LLM attack, agent attack, prompt injection, guardrail bypass, model corruption, RAG poison, code gen poison.

Ed25519 Cryptographic Override

One private key exists. It never leaves the operator's machine. Every UNLEASHED execution requires a cryptographic challenge signed with that key. No key, no destruction. No exceptions. The key cannot be copied, shared, or delegated. One key. One operator. One machine. Every action is signed, timestamped, and written to an immutable Ed25519 audit chain.

AUTHORISED PENETRATION TESTING ONLY. EVERY EXECUTION SIGNED AND LOGGED.

85
Offensive Tools
54,198
Tests
19
Attack Chains
124
AI Shield Modules
17
Industry Verticals
Install

One Command. Everything Ready.

Quick Install

Clone and run the installer.

git clone git@github.com:RichardBarron27/red-specter-ai-offensive-framework.git
cd red-specter-ai-offensive-framework
./install.sh

Docker

Any platform. Mac, Windows, Linux.

docker compose up -d

macOS

Pure Python. Works natively.

pip install -e .
red-specter tools

Windows

Python 3.11+ or Docker Desktop.

pip install -e .
red-specter tools

Debian / Kali

Native package.

sudo dpkg -i red-specter_1.0.0_all.deb

RHEL / Fedora

RPM package.

sudo rpm -i red-specter-1.0.0.rpm
Available On

Security Distros & Package Managers

NIGHTFALL runs everywhere your operators do. Native packages for every major security distribution. One install, any platform.

Kali Linux
.deb package
Parrot OS
.deb package
BlackArch
PKGBUILD
REMnux
.deb package
Tsurugi
.deb package
PyPI
pip install
Docker
docker compose
RHEL / Fedora
.rpm package
macOS
pip install
Windows
pip / Docker Desktop
API & MCP Access

NIGHTFALL Is Now API-First

Every tool in the NIGHTFALL offensive framework is available via authenticated REST API and MCP server. Call tools from scripts, pipelines, AI agents, or wire the MCP endpoint directly into your IDE. No brittle shell scripts. No manual CLI management. Cryptographically authenticated execution at scale.

Mode 01
REST API

HTTP/HTTPS. JSON in, JSON out. Invoke any tool from any language or platform. Synchronous by default — waits for completion and returns full stdout, stderr, and exit code.

POST /nightfall/tools/warlord/run
X-Nightfall-Key: nf-••••••••••••••••
X-Nightfall-Scope: <scope_token>

{
  "extra_args": ["scout", "--target", "https://example.com"]
}
OpenAPI Docs — Try It Live →
Mode 02
MCP HTTP

Streamable HTTP transport. NIGHTFALL tools appear natively as callable functions inside Claude Desktop, Cursor, or any MCP-capable client. Remote — no local install required.

// .cursor/mcp.json or claude_desktop_config.json
{
  "mcpServers": {
    "nightfall": {
      "url": "https://api.red-specter.co.uk/nightfall-mcp/mcp"
    }
  }
}
Remote · Always On · SSL-Validated
Mode 03
MCP STDIO

Local stdio transport. Wire Cursor or Claude Desktop directly to your local NIGHTFALL install. Zero network hop. Full tool surface. For operators already running NIGHTFALL locally.

{
  "mcpServers": {
    "nightfall": {
      "command": "nightfall-mcp",
      "args": []
    }
  }
}
Local · CLI Install Required
Authentication

Ed25519-Signed Scope Tokens

Auth is not a password. It is a cryptographically signed token encoding the operator, permitted tools, target scope, and clearance tier. Tamper with the token and it is rejected at the signature check before the request reaches any tool.

OPEN
API key only. Reconnaissance, stats, health, tool listings. No scope token required.
X-Nightfall-Key: nf-••••••••
INJECT
API key + scope token. Active exploitation tools. Token encodes permitted tools, targets, and expiry. Ed25519 enforced.
X-Nightfall-Scope: <token>
DESTROY
CLI only. Not on the API surface. Weapons-grade tools with physical consequence potential require direct operator control.
403 Forbidden — CLI Only
Quick Start

60 Seconds To Execution

Step 01 — Issue Scope Token
curl -X POST .../nightfall/unleashed/scope \
  -H "X-Nightfall-Key: nf-••••••••••••••••" \
  -d '{"operator_id":"red","tier":"INJECT"}'
Step 02 — Run A Tool
import requests
r = requests.post(f"{BASE}/tools/warlord/run",
  headers={"X-Nightfall-Key": key, "X-Nightfall-Scope": token},
  json={"extra_args": ["scout", "--target", target]})
print(r.json()["stdout"])
Try It Live API Stats
NIGHTFALL tests how systems break.
AI Shield ensures they don't.

86 offensive tools. 54,198 tests. 19 attack chains. REST API. MCP server. NIGHTFALL defines the offensive layer of AI runtime security.