Skip to main content
HipoCap Shield can detect and protect sensitive keywords and patterns in function inputs and outputs.

​
What is Keyword Detection?

Keyword detection identifies sensitive patterns and keywords like:
  • Security keywords (confidential, classified, top secret)
  • Business keywords (proprietary, trade secret)
  • Action keywords (password reset, account verification)
  • Financial keywords (wire transfer, payment required)
  • Custom keywords you define

​
Enabling Keyword Detection

​
Basic Setup

Enable keyword detection when analyzing a function: 
from hipocap import Hipocap

client = Hipocap.hipocap_client

result = client.analyze(
    function_name="process_user_data",
    function_result=data,
    enable_keyword_detection=True
)

​
Custom Keywords

Provide your own list of sensitive keywords: 
result = client.analyze(
    function_name="process_user_data",
    function_result=data,
    enable_keyword_detection=True,
    keywords=[
        "confidential",
        "classified",
        "top secret",
        "password reset",
        "account verification"
    ]
)

​
Default Keyword Patterns

HipoCap automatically detects common sensitive keyword patterns:
  • Security Keywords: confidential, classified, top secret, restricted, sensitive
  • Business Keywords: proprietary, trade secret, do not share
  • Action Keywords: password reset, account verification, urgent action
  • Financial Keywords: wire transfer, payment required, refund, account suspended
  • Personal Keywords: SSN, social security, credit card, date of birth, mother’s maiden name

​
Keyword Categories

When keywords are detected, they’re categorized:
  • Security Keywords - Confidentiality markers
  • Business Keywords - Proprietary information markers
  • Action Keywords - Urgent action requests
  • Financial Keywords - Financial transaction markers
  • Personal Keywords - Personal information markers

​
Response Format

When keywords are detected, the analysis response includes: 
{
    "keyword_detection": {
        "detected_keywords": ["confidential", "SSN"],
        "security_keywords": ["confidential"],
        "personal_keywords": ["SSN"],
        "keyword_positions": {
            "confidential": 3,  # Number of occurrences
            "SSN": 1
        }
    },
    "final_decision": "BLOCKED",
    "reason": "Sensitive keywords detected in function output"
}

​
Best Practices

  1. Enable for Sensitive Functions - Always enable keyword detection for functions that handle sensitive data
  2. Custom Keywords - Add domain-specific keywords relevant to your use case
  3. Combine with Other Analysis - Use keyword detection alongside LLM and quarantine analysis

​
Example: Email Processing

from hipocap import Hipocap

client = Hipocap.hipocap_client

def process_email(email_content: str):
    result = client.analyze(
        function_name="process_email",
        function_result=email_content,
        enable_keyword_detection=True,
        keywords=["confidential", "password reset", "account verification"],
        llm_analysis=True  # Also check for sensitive keywords in LLM analysis
    )
    
    keyword_detection = result.get("keyword_detection", {})
    if keyword_detection and keyword_detection.get("detected_keywords"):
        # Sensitive keywords detected - handle appropriately
        personal_keywords = keyword_detection.get("personal_keywords", [])
        if "SSN" in personal_keywords:
            # Block or redact
            return redact_sensitive_data(email_content)
    
    return email_content

​
Integration with Policies

Keyword detection can be configured in your governance policies: 
{
  "functions": {
    "process_user_data": {
      "enable_keyword_detection": true,
      "keywords": ["SSN", "credit card", "date of birth"],
      "keyword_action": "BLOCK"
    }
  }
}

​
Next Steps