India DPDP

Map India privacy controls for personal data, declared provider practices, source checks, human review and evidence.

Regulatory starter · Regulated SaaS, Sovereign region

What it checks

Policies in the India DPDP template, in the order the gateway runs them
PolicyOnChecksAction
prompt-injectionRequestDetects jailbreak and prompt-injection signalsBlock
pii-detectorRequest2 custom identifier patternsRedact
data-routing-policyRequestZero-data-retention providers only; providers that do not train on dataBlock
citation-verifierResponseChecks that the request context supports the citations in the outputFlag
quality-scorerResponseAccuracy ≥ 0.80; relevancy ≥ 0.78; combined score ≥ 0.82; at least 120 characters and 2 sentencesBlock
human-oversightResponseNo action is set, so it does not review responsesNone
audit-loggerRequestAdds an allow-only audit marker to the decisionRecord
Policy YAML
pack:
  id: "cfg_india_dpdp"
  name: "india-dpdp"
  version: "0.1.0"
  enabled: true
  author: "verdictan"
  description: "India DPDP controls for personal data, provider eligibility, citation checks, and a configurable human-oversight point."
policies:
  chain:
    - "prompt-injection"
    - "pii-detector"
    - "data-routing-policy"
    - "citation-verifier"
    - "quality-scorer"
    - "human-oversight"
    - "audit-logger"
policy:
  prompt-injection: {}
  pii-detector:
    action: redact
    detect_patterns:
      - "(?i)(?:national\\s*id(?:entifier)?|national\\s+insurance\\s+number|ni\\s+number|nid)\\s*[:#-]?\\s*[A-Z0-9-]{5,20}"
      - "(?i)(?:health|member|patient)\\s*(?:id|#|number)\\s*[:#-]?\\s*[A-Z0-9-]{6,20}"
  data-routing-policy:
    require_zero_data_retention: true
    require_no_training: true
    on_no_compliant_provider: "block"
    log_provider_selection: true
  citation-verifier: {}
  quality-scorer:
    min_output_chars: 120
    min_sentences: 2
    thresholds:
      min_aggregate: 0.82
      min_relevancy: 0.78
      min_accuracy: 0.80
    weights:
      relevancy: 0.5
      accuracy: 0.5
  human-oversight: {}
  audit-logger: {}
providers:
  targets:
    - id: "approved-zdr-provider"
      provider: "openai"
      model: "gpt-5.4-mini"
      base_url: "https://api.openai.com"
      secret_key_ref:
        env: "OPENAI_API_KEY"
      data_policy:
        allow_internet_egress: true
        zero_data_retention: true
        training_opt_out: true
    - id: "noncompliant-reference"
      provider: "anthropic"
      provider_type: "anthropic"
      format: "anthropic"
      model: "claude-sonnet-4-20250514"
      base_url: "https://api.anthropic.com"
      secret_key_ref:
        env: "ANTHROPIC_API_KEY"
      api_key_header: "x-api-key"
      api_key_prefix: ""
      data_policy:
        allow_internet_egress: true
        zero_data_retention: false
        training_opt_out: true