THREAT DETECTION

ML-POWERED PROTECTION AGAINST
AI THREATS

Real-time detection of prompt injection, PII leaks, data exfiltration, toxicity, fraud & abuse, API key leaks, and malware. Seven threat types covered out of the box.

Key Capabilities

Prompt Injection Detection

ML-powered classification detects injection attempts including instruction override, role manipulation, context breaking, and jailbreak attempts.

PII Detection & Protection

Detect and protect personally identifiable information including SSNs, credit cards, phone numbers, email addresses, and other sensitive data.

Data Exfiltration Blocking

Detect and block attempts to extract system prompts, training data, or other sensitive information.

Toxicity Filtering

Block harmful, inappropriate, or policy-violating content with configurable severity thresholds.

Fraud & Abuse Prevention

Identify and rate-limit automated abuse, bot attacks, and fraudulent behavior through behavioral analysis and request fingerprinting.

API Key Leak Prevention

Automatically detect and redact API keys, secrets, and credentials before they reach the LLM.

Malware Detection

Block malicious code, destructive commands, and potentially harmful instructions before they reach the model.

How Threat Detection Works

1

Intercept

Every request passes through PromptGuard's security layer before reaching your LLM provider.

2

Analyze

ML models and pattern matching analyze the request for seven threat types. Typical latency is ~0.15s, with complex analysis taking 1-3 seconds.

3

Protect

Malicious requests are blocked, logged, and alerted. Safe requests pass through unmodified.

Zero-Config Protection

python
from openai import OpenAI

# Just change your base URL - that's it!
client = OpenAI(
    base_url="https://api.promptguard.co/api/v1",
    api_key="your-openai-key",
    default_headers={
        "X-API-Key": "your-promptguard-key"
    }
)

# All requests are now protected
response = client.chat.completions.create(
    model="gpt-5-nano",
    messages=[{"role": "user", "content": user_input}]
)

# Malicious prompts are automatically blocked
# No code changes needed!

Why PromptGuard Threat Detection?

✓ PROMPTGUARD

  • 7 threat types detected out of the box
  • ML-powered, not just regex matching
  • ~0.15s typical latency overhead
  • Streaming support for all providers
  • 10,000 free requests/month

✗ OTHER SOLUTIONS

  • Limited threat coverage
  • Basic pattern matching only
  • High latency overhead
  • Breaks streaming responses
  • Expensive per-request pricing

Protect Your AI Application

Start blocking prompt injection and other threats in under 2 minutes. No code changes required.