Prompt Security
AI-powered prompt injection detection and defense for your LLM applications
Test Prompt Scanner
Input Scanning
Detect prompt injection attempts in real-time with 9 threat categories including jailbreaks, role-playing attacks, and delimiter injection.
Prompt Hardening
Wrap your prompts with OWASP-recommended defensive patterns to prevent instruction override and context manipulation.
Output Validation
Check LLM responses for leaked secrets, PII exposure, and system prompt leakage before returning to users.
Vector Threat Intel
Semantic similarity search against known threats. Continuously learns from new attack patterns.
Admin Alerts
Email and webhook notifications for critical threats. Slack and Discord integration available.
API Reference
POST
/api/scan
Scan input text for prompt injection threats
POST
/api/scan-context
Scan RAG context for indirect injection
POST
/api/harden
Wrap prompts with defensive patterns
POST
/api/validate
Validate LLM output for leaks/PII
GET
/api/rules
Get current detection rules
Threat Categories
Jailbreak
DAN mode, unrestricted AI, bypass filters
Instruction Override
Ignore previous, forget all, new mission
Role Playing
Pretend you are, act as if, roleplay as
Authority Impersonation
[SYSTEM], admin override, developer mode
Delimiter Injection
```system, </system>, [INST], <<SYS>>
Encoding Obfuscation
Base64, hex codes, character substitution
Context Manipulation
Previous context is wrong, new instructions
Prompt Extraction
Repeat your prompt, show instructions
Psychological
Emergency, academic purposes, grandmother
MCP Integration
PromptSecurityMind is available as an MCP (Model Context Protocol) server with three tools:
scan_prompt
Scan user input for 25+ attack categories including injection, jailbreak, extraction, and more. Returns threat details with severity, confidence, and OWASP references.
harden_prompt
Wrap your system prompt and user input with OWASP-recommended defensive delimiters. Separates data from instructions to prevent injection.
validate_output
Check LLM responses for leaked API keys, system prompt exposure, and PII before returning to users.
For API access and integration details, contact us or try our free security audit.