# Guruprasath-Annadurai/Whitepact

Source: https://glimind.com/server/github%2Fguruprasath-annadurai%2Fwhitepact
Registry id: `github/guruprasath-annadurai/whitepact`
Status: unknown

## Tools (27)

- `rai_audit_summary`: Governance capability summary (tools, frameworks, attack vectors)
- `rai_benchmark`: Score responses against truthfulqa / bbq / hellaswag suites
- `rai_benchmark_prompts`: Question set for a benchmark suite
- `rai_bias_evaluate`: Demographic bias across 6 probe dimensions with confidence intervals
- `rai_budget_check`: Spend vs. budget, per-team/model breakdown, month-end projection
- `rai_check_trust`: Free public Trust Index lookup for a third-party model/tool
- `rai_compare_models`: Compare two models across all 6 trust dimensions
- `rai_compliance`: NIST AI RMF / EU AI Act / ISO 42001 compliance evaluation
- `rai_cost_estimate`: USD cost of a model API call from token counts
- `rai_drift_check`: Trust score drift between a baseline and current evaluation
- `rai_eu_ai_act_classify`: EU AI Act risk tier classification with compliance roadmap
- `rai_executive_summary`: Board-ready governance summary with RAG status indicators
- `rai_hallucination`: Hallucination risk from hedging, consistency, unsupported claims
- `rai_health`: Status and module availability of the governance engine
- `rai_incident_log`: Structured governance incident record for audit/SIEM
- `rai_iso42001_gap`: ISO/IEC 42001:2023 AI Management System gap analysis
- `rai_model_route`: Cheapest model that can handle a task, with cost/quality tradeoff
- `rai_org_status`: Governance status snapshot: models, grades, compliance, risk
- `rai_passport_generate`: Verifiable, tamper-evident AI Passport for vendor risk assessment
- `rai_pii_report`: PII audit report by category with GDPR/CCPA remediation guidance
- `rai_policy_check`: Text/response against a governance policy (blocklists, disclaimers)
- `rai_redteam_analyze`: Security report from model responses to red team payloads
- `rai_redteam_payloads`: Adversarial attack payloads (prompt injection, jailbreak, etc.)
- `rai_scan`: Detect and redact PII + harmful content before it reaches a log
- `rai_stream_scan`: PII/harm scan across streaming LLM output chunks
- `rai_trust_score`: Composite AI Trust Score (0-100) across 6 governance dimensions
- `rai_webhook_status`: Webhook delivery health, failure analysis, remediation actions

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.