Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.promptguard.co/llms.txt

Use this file to discover all available pages before exploring further.

PromptGuard is built with enterprise security requirements in mind. This page outlines our security practices, compliance status, and data handling policies.

​
Security Certifications

CertificationStatusDetails
SOC 2 Type IIIn ProgressExpected Q2 2026
GDPRCompliantEU data processing agreement available
CCPACompliantCalifornia consumer privacy rights
EU AI ActAlignedTechnical controls map to Articles 9, 11, 12, 13, 14, 15
ISO/IEC 42001AlignedAI management system controls for risk, logging, transparency, oversight
ISO 27001PlannedOn roadmap for 2026
HIPAAPlannedContact sales for roadmap
“Aligned” means PromptGuard provides the technical controls that satisfy the framework’s requirements. Formal certification (where applicable) requires third-party audit. For enterprise customers requiring specific compliance certifications, contact sales@promptguard.co to discuss your requirements.

​
EU AI Act Alignment

The EU AI Act (Regulation 2024/1689) imposes requirements on high-risk AI systems, enforceable from August 2, 2026. PromptGuard provides technical controls that map to each requirement:
EU AI Act ArticleRequirementPromptGuard Capability
Art. 9 — Risk ManagementSystematic risk identification, analysis, and mitigation throughout the AI lifecyclePolicy engine with configurable threat detection (14 detector types, 1000+ patterns), per-request risk scoring, behavioral analysis
Art. 11 — Technical DocumentationMaintain documentation demonstrating risk management and system behaviorOpenAPI spec auto-generated from live API, governance reports with narrative sections, evidence packages for auditors
Art. 12 — Record-KeepingAutomatic recording of events enabling risk identification and post-market monitoringSOC 2 audit trail with tamper-evident hash chaining, every security decision logged with event ID, threat type, confidence, and timestamp
Art. 13 — TransparencyEnable deployers to interpret output and use the system appropriatelyPer-decision explainability (threat type, confidence, matched detectors), governance reports with incident timelines
Art. 14 — Human OversightMechanisms for human oversight, intervention, and overrideDashboard with real-time visibility, configurable alert thresholds, manual policy overrides, role-based access
Art. 15 — Accuracy, Robustness, CybersecurityMeet standards for accuracy, resilience to attacks, and cybersecurityEvaluated at F1=0.887 on 2,369 adversarial samples, automated red team testing, agent identity with cryptographic credentials, behavioral drift detection

​
ISO/IEC 42001 Alignment

ISO/IEC 42001:2023 is the international standard for AI Management Systems. PromptGuard’s controls map to its Annex A requirements:
ISO 42001 ControlRequirementPromptGuard Capability
Risk Assessment (6.1)Identify and assess AI-specific risks including security, misuse, and safety14 threat detector types covering OWASP LLM Top 10, configurable policy presets, per-request risk scoring
Data Governance (Annex A)Ensure data is appropriate, accurate, and free from harmful biases39-type PII detection and redaction, pass-through architecture with zero data retention, content safety classification
Transparency (Annex A)Provide transparency about AI system use and decision rationalePer-decision explainability, governance reports, audit trail with full decision context
Human Oversight (Annex A)Allow intervention and override capabilitiesDashboard with real-time monitoring, configurable block/allow/redact policies, manual credential rotation and revocation
Monitoring (Annex A)Detect and measure AI system behavior over timeBehavioral drift detection with Jensen-Shannon divergence, anomaly alerting, agent statistics tracking
Incident Response (10)Detect, respond to, and learn from AI system failuresReal-time threat alerts, webhook notifications, tamper-evident audit trail for forensic analysis, governance reports with incident timelines

​
Data Handling

​
What Data We Process

Data TypeProcessingRetention
Prompts & MessagesScanned for threats in memoryNot stored (pass-through)
API KeysEncrypted at rest (AES-256)Until deleted
Usage MetricsAggregated counts90 days
Security EventsThreat details logged30 days (configurable)
Audit LogsUser actions90 days

​
Data Flow

​
Pass-Through Architecture

PromptGuard operates as a pass-through proxy:
  • Prompts and responses are scanned in memory
  • Content is not stored after processing
  • Only metadata (timestamps, threat types, confidence scores) is logged
  • Your data never touches disk in unencrypted form
Security event logs may contain sanitized snippets of blocked content for debugging purposes. These are automatically purged after the retention period. Enterprise customers can disable content logging entirely.

​
Infrastructure Security

​
Cloud Infrastructure

ComponentProviderSecurity
ComputeGoogle Cloud RunServerless, auto-scaling
DatabaseSupabase (PostgreSQL)Encrypted at rest, TLS in transit
SecretsGoogle Secret ManagerIAM-controlled access
CDN/DDoSGoogle Cloud ArmorRate limiting, WAF
DNSCloudflareDDoS protection

​
Encryption

LayerStandard
In TransitTLS 1.3
At RestAES-256
API KeysArgon2id hashing
SecretsGoogle KMS

​
Network Security

  • All endpoints require HTTPS
  • Cloud Armor rate limiting (600 req/min per IP)
  • No public SSH access to infrastructure
  • VPC-based isolation between services
  • Private database connections (no public IP)

​
Access Control

​
Authentication Methods

MethodUse Case
API KeyServer-to-server, SDK integrations
Session (JWT)Dashboard access
OAuthGitHub/Google SSO
SAML/OIDCEnterprise SSO (Enterprise tier)

​
API Key Security

  • Keys are hashed with Argon2id before storage
  • Only the prefix (pg_xxxx...) is stored in plain text
  • Full key shown only once at creation
  • Keys can be rotated without downtime
  • Project-scoped API keys (no per-key permission types; tier gating via subscription)

​
Role-Based Access (Enterprise)

RolePermissions
OwnerFull access, billing, delete organization
AdminManage users, projects, settings
MemberView projects, create API keys
ViewerRead-only dashboard access

​
Audit Logging

​
What’s Logged

EventDetails Captured
AuthenticationLogin, logout, failed attempts
API Key ManagementCreate, rotate, delete
Project ChangesSettings, policies, presets
Security EventsBlocked requests, threat types
User ManagementInvites, role changes

​
Accessing Audit Logs

  1. Go to Dashboard → Settings → Audit Logs
  2. Filter by date range, event type, or user
  3. Export as CSV or JSON

​
Log Export (Enterprise)

Enterprise customers can configure:
  • SIEM Integration: Stream logs to Splunk, Datadog, etc.
  • S3 Export: Daily log exports to your bucket
  • Webhook: Real-time log forwarding

​
Incident Response

​
Security Incident Process

  1. Detection: Automated monitoring + manual review
  2. Containment: Isolate affected systems
  3. Investigation: Root cause analysis
  4. Notification: Affected customers notified within 72 hours
  5. Remediation: Fix deployed, post-mortem published

​
Reporting Security Issues

Found a vulnerability? Contact us:

​
Data Residency

​
Current Regions

RegionData Center
USGoogle Cloud us-central1 (Iowa)

​
Planned Regions

RegionStatus
EU (Frankfurt)Q3 2026
APAC (Singapore)Q4 2026
Enterprise customers requiring specific data residency can request dedicated deployment in their preferred region.

​
Vendor Security

​
Subprocessors

VendorPurposeData Processed
Google CloudInfrastructureAll data
SupabaseDatabaseMetadata, logs
StripeBillingPayment info
ResendEmailEmail addresses

​
LLM Providers

PromptGuard forwards requests to your chosen LLM provider. We do not store data sent to:
  • OpenAI
  • Anthropic
  • Google AI
  • Cohere
  • AWS Bedrock
  • Azure OpenAI
Your data handling agreement is with each LLM provider directly.

​
AI Agent Governance

PromptGuard provides four governance capabilities for AI agents operating in production:

​
Agent Identity

Register agents with verified cryptographic credentials. Each agent receives a unique pgag_ secret that authenticates tool-call and guard requests. Self-asserted agent IDs still work (backward compatible), but verified agents get explicit identity confirmation in audit logs and governance reports.
  • POST /api/v1/agent/register — Register and receive a one-time credential
  • POST /api/v1/agent/{agent_id}/rotate-credential — Revoke old credential, issue new one
  • X-Agent-Credential header for verified requests

​
Behavioral Drift Detection

After an agent accumulates sufficient observations, PromptGuard freezes a behavioral baseline capturing the agent’s normal tool-usage distribution. Every subsequent request is compared against this baseline using Jensen-Shannon divergence. If the distribution shifts beyond the configured threshold, a BEHAVIORAL_DRIFT alert fires.

​
Tamper-Evident Audit Trail

Every audit event’s SHA-256 hash incorporates the previous event’s hash, forming a cryptographic chain. If any event is modified or deleted, the chain breaks and verification fails. Use POST /dashboard/audit-log/verify-chain to verify chain integrity over any time range.

​
Governance Reports

Generate auditor-facing narrative reports covering all four governance capabilities: 
curl -X POST https://api.promptguard.co/dashboard/compliance/governance-report \
  -H "Cookie: session=YOUR_SESSION_COOKIE" \
  -d "framework=soc2&days=30"
The report includes sections for agent identity verification rates, behavioral drift alerts, audit chain integrity status, security decision summaries, and a chronological incident timeline.

​
Enterprise Security Features

Available on the Enterprise tier:
FeatureDescription
Self-Hosted DeploymentRun PromptGuard in your own infrastructure
Air-Gapped ModeZero external network calls
SSO (SAML/OIDC)Integrate with your IdP
IP AllowlistingRestrict API access by IP
Custom Data RetentionConfigure log retention periods
Dedicated SupportSLA-backed support with named contact
Custom BAAHIPAA Business Associate Agreement (planned)

​
Security Questionnaire

Need to complete a vendor security assessment? We provide:
  • CAIQ (Consensus Assessment Initiative Questionnaire)
  • SIG Lite (Standardized Information Gathering)
  • Custom Questionnaires (for Enterprise customers)
Contact security@promptguard.co for these documents.

​
Responsible Disclosure

We appreciate security researchers who help keep PromptGuard secure:
  1. Report the issue to security@promptguard.co
  2. Do not publicly disclose until we’ve addressed it
  3. Provide steps to reproduce
  4. Allow reasonable time for remediation (90 days)

​
Next Steps

Security Overview

Learn about threat detection

Audit Logs

Monitor user activity

Enterprise

See Enterprise features

Contact Sales

Discuss your requirements