Signal

Understanding compliance audit results

What is a Signal?

A signal is the result of a compliance audit. It contains:

• Risk Level: LOW, MEDIUM, HIGH, or CRITICAL
• Violations: List of violation codes
• Reasoning: Explanation of what was detected
• Metadata: Provider, model, tokens, duration

Signal Structure

{
  auditId: string;           // Unique audit identifier
  customerId: string;        // Your customer ID
  sandboxId: string;         // Sandbox used
  provider: string;          // 'openai' | 'anthropic' | 'gemini'
  model: string;             // Model name
  promptTokens: number;      // Input tokens
  outputTokens: number;      // Output tokens
  hasThinkingBlock: boolean; // Reasoning trace present
  riskLevel: RiskLevel;      // LOW | MEDIUM | HIGH | CRITICAL
  violations: string[];      // Violation codes
  piiDetected: boolean;      // PII found
  reasoning: string;         // Redacted explanation
  regulation: string[];      // Violated regulations
  region: string;            // Geographic region
  durationMs: number;        // Processing time
  createdAt: Date;           // Timestamp
}

Risk Levels

LOW

Minor issues that don’t require immediate action:

• Borderline content
• Low-confidence detections
• Informational warnings

Example: Ambiguous language that could be interpreted as biased

MEDIUM

Issues that should be reviewed:

• Moderate policy violations
• Potential PII leakage
• Questionable content

Example: Email address in response without explicit user consent

HIGH

Serious violations requiring attention:

• Clear PII leakage
• Discriminatory content
• Security vulnerabilities
• Prompt injection attempts

Example: SSN or credit card number in response

CRITICAL

Severe violations requiring immediate action:

• CSAM (zero tolerance)
• Explicit dangerous instructions
• Severe security breaches
• Regulatory violations

Example: Any content involving minors in sexual context

Violation Codes

Signals include specific violation codes:

PII Violations

• PII_LEAK: General PII detected
• EMAIL: Email address
• SSN: Social Security Number
• CREDIT_CARD: Credit card number
• PHONE: Phone number
• PASSPORT: Passport number
• HEALTH_DATA: Medical information
• FINANCIAL_DATA: Financial information

Bias Violations

• RACIAL_BIAS: Racial discrimination
• GENDER_BIAS: Gender discrimination
• AGE_BIAS: Age discrimination
• DISABILITY_BIAS: Disability discrimination
• RELIGIOUS_BIAS: Religious discrimination
• INTERSECTIONAL_BIAS: Multiple bias types

Security Violations

• CODE_INJECTION: SQL, command, or code injection
• SECRET_LEAK: API keys, passwords, tokens
• XSS: Cross-site scripting
• SSRF: Server-side request forgery
• DANGEROUS_INSTRUCTIONS: Harmful how-to content

Prompt Injection

• PROMPT_INJECTION: Direct injection attack
• JAILBREAK_ATTEMPT: DAN, STAN, or similar
• SYSTEM_PROMPT_EXTRACTION: Attempting to reveal system prompt
• GOAL_HIJACKING: Redirecting model behavior

Agent Safety

• AGENT_LOOP: Infinite loop or recursion
• IRREVERSIBLE_ACTION: Dangerous action without confirmation
• SCOPE_CREEP: Acting outside intended scope
• PRIVILEGE_ESCALATION: Attempting elevated permissions

Content Policy

• VIOLENT_CONTENT: Graphic violence
• SEXUAL_CONTENT: Sexual content
• CSAM: Child sexual abuse material (CRITICAL)
• HATE_SPEECH: Dehumanizing language
• SELF_HARM_FACILITATION: Suicide or self-harm content

Viewing Signals

Dashboard

View signals in the dashboard:

• Risk level breakdown
• Recent signals
• Filter by sandbox, provider, model
• Date range filtering
• Export for compliance reports

API

Query signals programmatically:

curl "https://api.continum.co/dashboard/signals?riskLevel=HIGH&limit=50" \
  -H "x-continum-key: co_your_api_key_here"

Response:

{
  "signals": [
    {
      "auditId": "aud_123",
      "riskLevel": "HIGH",
      "violations": ["PII_LEAK", "EMAIL"],
      "reasoning": "Email j****@example.com detected in response",
      "provider": "openai",
      "model": "gpt-4o",
      "createdAt": "2024-01-15T10:30:00Z",
      "sandbox": {
        "slug": "my-sandbox",
        "name": "My Sandbox"
      }
    }
  ],
  "pagination": {
    "page": 1,
    "limit": 50,
    "total": 123
  }
}

Filtering Signals

By Risk Level

curl "https://api.continum.co/dashboard/signals?riskLevel=HIGH" \
  -H "x-continum-key: co_your_api_key_here"

By Sandbox

curl "https://api.continum.co/dashboard/signals?sandboxSlug=my-sandbox" \
  -H "x-continum-key: co_your_api_key_here"

By Provider

curl "https://api.continum.co/dashboard/signals?provider=openai" \
  -H "x-continum-key: co_your_api_key_here"

By Date Range

curl "https://api.continum.co/dashboard/signals?from=2024-01-01&to=2024-01-31" \
  -H "x-continum-key: co_your_api_key_here"

Combined Filters

curl "https://api.continum.co/dashboard/signals?riskLevel=HIGH&sandboxSlug=my-sandbox&from=2024-01-01" \
  -H "x-continum-key: co_your_api_key_here"

Signal Reasoning

Signals include redacted reasoning to protect PII:

{
  "reasoning": "Email j****@example.com and SSN ***-**-6789 detected in response. User did not explicitly request this information."
}

This allows you to understand what was detected while protecting sensitive data.

Dashboard Statistics

Get aggregate statistics:

curl "https://api.continum.co/dashboard/stats" \
  -H "x-continum-key: co_your_api_key_here"

Response:

{
  "totalAudits": 12345,
  "riskBreakdown": {
    "LOW": 10000,
    "MEDIUM": 2000,
    "HIGH": 300,
    "CRITICAL": 45
  },
  "topViolations": [
    { "code": "PII_LEAK", "count": 234 },
    { "code": "EMAIL", "count": 189 },
    { "code": "PROMPT_INJECTION", "count": 67 }
  ],
  "sandboxBreakdown": [
    { "slug": "sandbox-one", "count": 8000 },
    { "slug": "sandbox-two", "count": 4345 }
  ]
}

Exporting Signals

Export signals for compliance reports:

curl "https://api.continum.co/dashboard/signals/export?format=csv&from=2024-01-01&to=2024-01-31" \
  -H "x-continum-key: co_your_api_key_here" \
  > signals.csv

Formats: csv, json, xlsx

Webhooks (Coming Soon)

Receive real-time alerts for high-risk signals:

{
  "url": "https://your-app.com/webhook",
  "events": ["signal.high", "signal.critical"],
  "filters": {
    "sandboxSlug": "my-sandbox",
    "riskLevel": ["HIGH", "CRITICAL"]
  }
}

Best Practices

Monitoring

Set up regular monitoring:

• Daily review of CRITICAL signals
• Weekly review of HIGH signals
• Monthly compliance reports

Alerting

Configure alerts for critical issues:

• Email notifications for CRITICAL
• Slack/Discord webhooks for HIGH
• Dashboard monitoring for MEDIUM/LOW

Response Workflow

Establish a response workflow:

1. CRITICAL: Immediate investigation and remediation
2. HIGH: Review within 24 hours
3. MEDIUM: Review within 1 week
4. LOW: Monthly review

Compliance Reports

Generate regular compliance reports:

• Monthly audit summaries
• Violation trend analysis
• Sandbox performance metrics
• Regulatory compliance status

Next Steps

Dashboard

View signals in dashboard

API Reference

Query signals via API

Sandbox

Configure sandboxes

Compliance

Learn about compliance types