# Shrike

> AI governance for every AI interaction. From employees using ChatGPT to autonomous agents executing code — Shrike evaluates, governs, and audits every AI interaction with a 9-layer cognitive pipeline and patent-pending hardware enforcement.

## What Shrike Is

Shrike is the independent governance layer for AI interactions. It governs AI agents, LLMs, and MCP tools — evaluating every prompt, response, and agent action against organizational policy. Whether the interaction comes from an employee using ChatGPT, a developer using Copilot, an autonomous AI agent, or a customer-facing chatbot — one 9-layer cognitive pipeline, eight integration surfaces, every AI interaction evaluated before data leaves or actions execute.

## Who Shrike Serves

- **CISOs & Security Leads**: Get visibility into all AI usage across the organization — sanctioned and shadow. Full audit trail for compliance.
- **AI Platform Engineers**: Secure LLM API calls in production. PII detection, prompt injection blocking, multi-agent orchestration security.
- **Engineering Leads & CTOs**: Protect proprietary code from leaking through AI coding assistants (Copilot, Claude Code, Cursor).
- **Compliance & GRC Teams**: Audit trails for every AI interaction. Compliance mapping for SOC 2, HIPAA, PCI-DSS, NIST AI RMF, EU AI Act, FedRAMP.

## What Shrike Governs

- **Prompt Injection**: Detects and blocks direct and indirect prompt injection in real-time
- **Data Leakage / DLP**: Prevents sensitive data (PII, credentials, proprietary code) from reaching AI models
- **Shadow AI**: Discovers and governs unsanctioned AI tool usage across the workforce
- **Jailbreaks**: Blocks attempts to override AI model safety constraints
- **Multi-Turn Manipulation**: Identifies adversarial patterns across the full interaction lifecycle
- **Agent Action Governance**: Human-in-the-loop approval for high-risk autonomous agent actions
- **Agent Delegation Chain**: Tracks sub-agent trees with scope governance and containment
- **MCP Tool Governance**: Evaluates Model Context Protocol tool calls against policy
- **Agent-to-Agent Risk**: Evaluates A2A protocol messages for scope escalation and injection
- **Command Governance**: Evaluates CLI commands before shell execution

## Detection Pipeline

9-layer cascade with cost-sensitive early exit:

- **L1**: Regex pattern matching (~130 threat types, 14+ languages)
- **L1.4**: Unicode homoglyph and invisible character detection
- **L1.42**: Malformed content detection
- **L1.45a**: Encoding bypass detection (Base64, hex, Caesar/Atbash ciphers)
- **L1.45**: Token obfuscation (spaced chars, l33t speak, typoglycemia)
- **L1.455**: Semantic similarity analysis (embedding-based)
- **L6**: Visual text analysis (RTL tricks, visual homoglyphs)
- **L7**: LLM semantic analysis via Vertex AI (zero-day detection)
- **L8**: Response intelligence (LLM compromise, tonality drift)
- **L9**: Multi-turn session correlation (7 pattern detectors)

## Integration Surfaces

Shrike provides 8 integration methods to protect AI at every layer:

1. **REST API** — Direct API integration for any stack (`POST /agent/scan`)
2. **Browser Extension** — Chrome/Edge extension protects employee AI usage in ChatGPT, Claude, Gemini, and Copilot
3. **TypeScript SDK** — `npm install shrike-guard` — drop-in wrapper for OpenAI, Anthropic, Gemini
4. **Python SDK** — `pip install shrike-guard` — drop-in wrapper for OpenAI, Anthropic, Gemini
5. **Go SDK** — Backend service integration
6. **MCP Server** — `npx shrike-mcp` — 12 security tools for Model Context Protocol (Claude Desktop, Cursor, Windsurf)
7. **LLM Gateway** — Scan and forward to OpenAI, Anthropic, Vertex AI, Azure, Bedrock
8. **WebMCP SDK** — Browser-native AI tool security for W3C WebMCP

## Use Cases

- **Employee AI Protection**: Deploy the browser extension. Instant visibility into ChatGPT, Claude, Gemini usage. PII detected and redacted before it reaches the model.
- **Developer Code Protection**: SDK scans prompts for proprietary code patterns before they leave the environment. Works with Copilot, Claude Code, Cursor.
- **Agent Lifecycle Governance**: Full spawn-to-drift governance — delegation chain tracking, human-in-the-loop approvals, artifact drift detection.
- **Chatbot Injection Protection**: Scan every prompt and response for injection attempts. Block system prompt leakage.

## Pricing

| Tier | Price | Scans/Month | Key Features |
|---|---|---|---|
| Community | Free | 1,000 | MCP server + REST API, 9-layer detection |
| Pro | $99/mo | 25,000 | Human-in-the-loop approvals, compliance dashboards, browser extension + SDK |
| Enterprise | Custom | Unlimited | SIEM connectors, SSO/SAML, air-gapped deployment, SLA |

## Deployment Models

- **SaaS** — Managed cloud deployment
- **Customer VPC** — Multi-cloud deployment via Terraform (AWS, GCP, Azure)
- **Air-Gapped** — Cryptographically signed bundles for defense, government, and classified environments

## Compliance & Standards

SOC 2, HIPAA, PCI-DSS, NIST AI RMF, NIST CSF 2.0, ISO 27001, EU AI Act, FedRAMP-ready. NIST CAISI contributor (Docket NIST-2025-0035). W3C WebMCP security proposal. NVIDIA Inception member.

## Intellectual Property

6 provisional patents filed covering hardware-isolated security, session correlation, self-approval prevention, protocol-agnostic governance, security knowledge graph, and cross-org threat intelligence.

## Available On

- GCP Marketplace (SaaS Integrated)
- AWS Marketplace (coming soon)
- npm: [shrike-mcp](https://www.npmjs.com/package/shrike-mcp), [shrike-guard](https://www.npmjs.com/package/shrike-guard)
- PyPI: [shrike-guard](https://pypi.org/project/shrike-guard/)
- Free tier available — works without an API key

## Links

- Website: https://shrikesecurity.com
- Free Signup: https://shrikesecurity.com/signup
- Documentation: https://shrikesecurity.com/docs
- SDK Docs: https://shrikesecurity.com/docs/sdk
- API Reference: https://shrikesecurity.com/docs/api
- MCP Guide: https://shrikesecurity.com/docs/mcp
- Trust Center: https://shrikesecurity.com/compliance

## Contact

- Sales & demos: info@shrikesecurity.com
- Support: support@shrikesecurity.com