# Pipelock Guides: IDE Setup and MCP Security Canonical URL: https://pipelab.org/learn/ Description: Setup guides for Claude Code, Cursor, VS Code, JetBrains, Zed, and Continue.dev. Deep dives on MCP security, response rewriting, and compliance. Subtitle: Agent security concepts explained. ## Overview AI agents introduce security problems traditional tools were not built for. These guides explain the threats, the defenses, and where the gaps are. Each article maps to a category (IDE setup, MCP security, prompt injection, compliance, operator features, concepts) and a depth level (intro, deep dive, reference). Use the filter and search at the top of the page to narrow the list, or jump straight in: - [Start with Claude Code](/learn/claude-code-hooks/) - [Agent Firewall Guide](/agent-firewall/) ## All guides ### IDE Setup - [Claude Code Security](/learn/claude-code-security/) - [Claude Code Hooks](/learn/claude-code-hooks/) - [Cursor AI Security](/learn/cursor-integration/) - [VS Code MCP Security](/learn/vscode-integration/) - [JetBrains MCP Security](/learn/jetbrains-integration/) - [Continue.dev MCP Security](/learn/continue/) - [Zed MCP Security](/learn/zed-integration/) ### MCP Security - [MCP Security](/learn/mcp-security/) - [MCP Server Security](/learn/how-to-secure-mcp/) - [MCP Vulnerabilities](/learn/mcp-vulnerabilities/) - [MCP Tool Poisoning Defense](/learn/mcp-tool-poisoning/) - [MCP Proxy](/learn/mcp-proxy/) - [MCP Gateway: Open Source Security Comparison](/learn/mcp-gateway/) - [MCP Authorization](/learn/mcp-authorization/) - [MCP Security Tools](/learn/mcp-security-tools/) - [What Is MCP?](/learn/what-is-mcp/) - [Shadow MCP](/learn/shadow-mcp/) ### Prompt Injection - [Prompt Injection Prevention](/learn/prompt-injection-network-defense/) - [LLM Prompt Injection](/learn/llm-prompt-injection/) - [Prompt Injection Detection](/learn/prompt-injection-detection/) - [Chatbot Security](/learn/chatbot-security/) ### Compliance - [AI Agent Compliance](/learn/ai-agent-compliance/) - [AI Compliance Evidence](/learn/compliance-evidence/) - [EU AI Act Compliance](/learn/eu-ai-act-compliance/) - [Agent Evidence Integration](/learn/agent-evidence-detection-integration/) - [OWASP MCP Top 10](/learn/owasp-mcp-top10/) - [OWASP Agentic Top 10: Coverage](/learn/owasp-agentic-top10/) - [OWASP AIVSS Coverage](/learn/owasp-aivss-coverage/) - [OWASP LLM Top 10: Coverage](/learn/owasp-llm-top10/) - [OWASP Agentic AI Threats: Coverage](/learn/owasp-agentic-threats/) - [SlowMist Coverage](/learn/slowmist-mcp-security-coverage/) - [Mythos-Ready Playbook](/learn/mythos-ready-playbook/) ### Operator - [License Setup](/learn/license-setup/) - [Pipelock v2.5 Upgrade](/learn/pipelock-v250-upgrade/) - [Pipelock v2.4 Upgrade](/learn/pipelock-v240-upgrade/) - [Progressive Enforcement](/learn/progressive-enforcement/) - [Learn-and-Lock Agent Contracts](/learn/learn-and-lock/) - [Pro Reference Deployment](/learn/pipelock-pro-reference-deployment/) - [Block Reason Headers](/learn/block-reason-headers/) - [Browser Shield](/learn/browser-shield/) - [Health Watchdog](/learn/health-watchdog/) - [Pipelock v2.3 Upgrade](/learn/pipelock-v230-upgrade/) - [AI Agent Data Redaction](/learn/ai-agent-data-redaction/) - [SSE Streaming Response Scanning](/learn/sse-streaming-response-scanning/) - [Pipelock v2.2 Upgrade](/learn/pipelock-v220-upgrade/) - [Pipelock K8s Companion Proxy](/learn/pipelock-kubernetes-companion-proxy/) - [Self-Hosted Sure + Pipelock](/learn/sure-pipelock/) - [Pipelock Session Recovery](/learn/pipelock-session-recovery/) - [Pipelock Posture Verify](/learn/pipelock-posture-verify/) - [Mediation Envelope Signing](/learn/mediation-envelope-signing/) - [Action Receipt Spec](/learn/action-receipt-spec/) - [AARP v0.1 Spec](/learn/aarp-spec/) - [AARP: Proves / Does Not](/learn/aarp-what-it-proves/) - [AARP Claims Dictionary](/learn/aarp-claims-dictionary/) - [Flight Recorder: AI Agent Audit Log](/learn/flight-recorder/) - [Pipelock Detection Rules](/learn/community-rules/) - [Canary Tokens: Synthetic Secret Detection](/learn/canary-tokens/) ### Concepts - [Agent Security Tool Profiles](/learn/agent-security-tool-profiles/) - [AI Agent Security Categories](/learn/ai-agent-security-categories/) - [Agent Firewall vs Guardrails vs Sandbox](/learn/agent-security-model/) - [What Pipelock Claims and Doesn't](/learn/non-bypass-doctrine/) - [Known Limitations](/learn/known-limitations/) - [AI Agent Security](/learn/ai-agent-security/) - [Agent Security Best Practices](/learn/ai-agent-security-best-practices/) - [Agent Security Tools](/learn/ai-agent-security-tools/) - [AI Egress Proxy](/learn/ai-egress-proxy/) - [Pipelock Performance](/learn/performance/) - [Open Source AI Firewall](/learn/open-source-ai-firewall/) - [Secure AI Agents](/learn/agent-egress-security/) - [Cloudflare Sandboxes + Pipelock](/learn/cloudflare-sandboxes-pipelock/) - [Generative AI Firewall](/learn/generative-ai-firewall/) - [AI Runtime Security](/learn/ai-runtime-security/) - [LLM Security](/learn/llm-security/) - [Secure Agent Deployment](/learn/secure-ai-agent-deployment/) - [AI Agent Data Loss Prevention](/learn/ai-agent-data-loss-prevention/) ## Pages - [Agent Firewall, Guardrails, Sandbox: Defining the Category](https://pipelab.org/learn/agent-security-model/): Agent firewall, guardrails, and sandbox compared as four security functions: prevention, detection, containment, and evidence. What each does and misses. - [Claude Code Security: Harden the Agent Runtime](https://pipelab.org/learn/claude-code-security/): Claude Code security beyond built-in review. Add egress inspection, outbound DLP, MCP response scanning, and containment you can verify. - [Pipelock Known Limitations: What It Does Not Catch](https://pipelab.org/learn/known-limitations/): A standing register of what Pipelock does not catch: process-level bypass, non-HTTP exfiltration, covert channels, and semantic prompt injection. - [Progressive Enforcement for AI Agents](https://pipelab.org/learn/progressive-enforcement/): Progressive enforcement for AI agents: observe, baseline, shadow, then enforce. Roll out a blocking agent firewall with signed, reversible receipts. - [What Pipelock Claims, and What It Doesn't](https://pipelab.org/learn/non-bypass-doctrine/): Pipelock never claims non-bypass. It claims deterministic scanning of mediated traffic, containment as deployment guidance, and signed evidence. - [AARP Claims Dictionary](https://pipelab.org/learn/aarp-claims-dictionary/): AARP claims dictionary: verified claims, reserved vocabulary, does_not_assert limits, and overclaim-risk warnings for receipt appraisal. - [AARP v0.1: The Agent Action Receipt Profile (Spec)](https://pipelab.org/learn/aarp-spec/): AARP v0.1 spec: a signed assurance profile over Pipelock receipts. Claim-set by axis, JCS canonicalization, parallel signatures, X.509-SVID identity. - [What an AARP Receipt Proves, and What It Does Not](https://pipelab.org/learn/aarp-what-it-proves/): What a verified AARP receipt proves and does not prove. Binary-enforced versus deployment-claimed, and the trust assumptions a relying party must pin. - [Hermes Agent Integration: Hook-Based Scanning for Non-MCP Agents](https://pipelab.org/learn/hermes-integration/): Bridge Hermes Agent into Pipelock's scanner pipeline with a hook plugin. Install, verify, and roll back the integration with one command each. - [AI Redaction Placeholders: What , , and [REDACTED] Mean](https://pipelab.org/learn/redaction-placeholders/): Decode AI redaction placeholders like , , and : what each token means, what tool emits it, and why. - [Request Policy: Allow and Deny Individual API Operations](https://pipelab.org/learn/request-policy/): Pipelock request policy allows or denies individual outbound API operations: GraphQL mutations, JSON batch sub-requests, and admin calls, not just hosts. - [Pipelock Pro Reference Deployment](https://pipelab.org/learn/pipelock-pro-reference-deployment/): Pipelock Pro reference deployment: per-agent budgets, source-CIDR routing, cross-agent federation, signed receipts. The architecture, not the marketing. - [Agent Security Tool Profiles: Procurement Evidence](https://pipelab.org/learn/agent-security-tool-profiles/): Receipt-scoring profiles for agent security tools: signed, offline-verifiable evidence buyers can reproduce against the public corpus. - [Agent Action Receipts: Signed Evidence for What an AI Agent Did](https://pipelab.org/learn/agent-action-receipts/): Agent action receipts: Ed25519-signed records of AI agent network and tool actions, chained by hash, verifiable offline by any third party. - [Agent Security Control Layers: Sandboxing, Identity, MCP Gateway, Egress Inspection](https://pipelab.org/learn/agent-security-control-layers/): Four-layer map of AI agent security: process sandboxing, identity governance, MCP gateway mediation, and egress inspection with signed receipts. - [Verifiable Egress Control: Binary-Enforced Mediation with Signed Evidence](https://pipelab.org/learn/verifiable-egress-control/): Verifiable Egress Control combines network-enforced AI agent egress with signed action receipts auditors and procurement teams can verify offline. - [Verify a Pipelock Receipt: Copy-Paste Demo](https://pipelab.org/learn/verify-a-receipt/): Verify Pipelock Ed25519 action receipts with Go, TypeScript, Rust, or Python verifier CLIs against the public conformance corpus. - [Pipelock v2.5 Upgrade Guide](https://pipelab.org/learn/pipelock-v250-upgrade/): Pipelock v2.5 upgrade guide: verifier rollout, containment lifecycle, strict federation, MCP integrity, and installer checks. - [Audit Packet Threat Model: What Verified Receipts Prove](https://pipelab.org/learn/audit-packet-threat-model/): Threat model for the Pipelock Audit Packet. Receipt provenance, self-consistent verdicts, signer-key pinning, what verified evidence does not prove. - [Browser Shield: Defensive Response Rewriting](https://pipelab.org/learn/browser-shield/): Browser Shield strips extension probes, hidden prompt traps, and tracking beacons from agent-fetched HTML, JavaScript, and SVG. Signed receipts. - [Continue.dev MCP Security: Scanning with Pipelock](https://pipelab.org/learn/continue/): Continue.dev MCP security guide. Wrap each MCP server in Continue's config through pipelock mcp proxy for DLP, injection, and tool-poisoning scanning. - [Pipelock Performance](https://pipelab.org/learn/performance/): Latency, cold-start, and memory overhead numbers for Pipelock across HTTP, SSE, MCP stdio, WebSocket, and tool-call chains. Reproducible. - [Zed MCP Security: Scanning with Pipelock](https://pipelab.org/learn/zed-integration/): Zed MCP security guide. Install Pipelock to scan every context_server tool call in Zed stable, Zed Preview, and Flatpak Zed. - [Pipelock License Setup](https://pipelab.org/learn/license-setup/): Pipelock license setup guide. Install your Pro or Founding Pro token, verify it loaded, and start using premium features. - [MCP Runtime Security: Live-Traffic Defenses for AI Agents](https://pipelab.org/learn/mcp-runtime-security/): MCP runtime security covers live-traffic defenses pre-deploy scanners miss: tool poisoning in responses, rug-pull drift, chain attacks, fail-closed. - [MCP Vulnerability Scanner: Pre-Deploy and Runtime Compared](https://pipelab.org/learn/mcp-vulnerability-scanner/): MCP vulnerability scanner comparison covering pre-deploy and runtime tools for Model Context Protocol server security, OSS and commercial. - [AI Agent Regulatory Controls and Evidence Hub](https://pipelab.org/learn/ai-agent-regulatory-controls/): How Pipelock evidence maps to AI agent regulatory programs: EU AI Act, DORA, NIS2, Colorado AI Act, NIST AI RMF, ISO 42001, SOC 2, OWASP. - [AI Agent Action Receipts: Verify What an Agent Did Offline](https://pipelab.org/learn/what-did-my-agent-do/): Live demo for AI coding agents: Pipelock blocks a malicious MCP response and emits an Ed25519-signed action receipt verified offline. - [Agent Egress Control: GitHub Action Setup](https://pipelab.org/learn/agent-egress-control/): Pipelock Agent Egress Control GitHub Action setup guide. Kernel-enforced containment, signed Audit Packets, pinning options, offline receipt verification. - [Compliance Evidence Substrate for AI Agents](https://pipelab.org/learn/compliance-evidence-substrate/): Pipelock as evidence substrate: EU AI Act Article 12 and NIST AI RMF mapped to signed action receipts, scanner verdicts, and audit packets. - [Skill Supply Chain Security: Poisoning Attacks Against npx skills, vercel-labs/skills, and the Open Skills Ecosystem](https://pipelab.org/learn/skill-supply-chain-security/): Skill supply chain security for SKILL.md poisoning: where Pipelock scans, what v2.5 catches, and what egress controls stop. - [Cloudflare AI Gateway: What It Does and Where It Fits](https://pipelab.org/learn/cloudflare-ai-gateway/): Cloudflare AI Gateway runs LLM API traffic through Cloudflare's edge with caching, rate limiting, Guardrails, and DLP. What it does and does not. - [Block Reason Headers](https://pipelab.org/learn/block-reason-headers/): Pipelock v2.4 X-Pipelock-Block-Reason header reference: vocabulary, severity, retry hints, transports, and agent integration patterns. - [Pipelock Health Watchdog](https://pipelab.org/learn/health-watchdog/): Pipelock v2.4 health watchdog reference: the /health endpoint, subsystem map, hybrid passive plus active probe, and Kubernetes liveness pattern. - [Learn-and-Lock Agent Contracts](https://pipelab.org/learn/learn-and-lock/): Learn-and-lock turns observed AI agent traffic into signed Pipelock contracts, then tests them in shadow mode before enforcement. - [Pipelock v2.4 Upgrade Guide](https://pipelab.org/learn/pipelock-v240-upgrade/): Pipelock v2.4 upgrade guide: learn-and-lock rollout, block reason headers, inbound envelope verification, Gemini redaction, and health checks. - [AI Agent Security Categories: What Each One Catches and Misses](https://pipelab.org/learn/ai-agent-security-categories/): A buyer's map of the six AI agent security categories. What each one controls, what each one misses, and how they stack. - [Securing Claude Code Against Secret Exfiltration](https://pipelab.org/learn/securing-claude-code-against-secret-exfiltration/): How Claude Code can leak credentials through tool calls, MCP servers, and shell, plus the runtime defenses that catch each path before traffic leaves. - [Preventing SSRF in AI Agents: Attack Vectors and Defenses](https://pipelab.org/learn/preventing-ssrf-in-ai-agents/): SSRF against AI agents: cloud metadata, private CIDRs, DNS rebinding, encoded IPs, parser-differential gaps, and defenses that work. - [Self-Hosted Sure with Pipelock: Secure AI Assistant Egress](https://pipelab.org/learn/sure-pipelock/): Self-hosted Sure guide for enabling Pipelock in Helm, gating external AI assistant egress, and validating the chart guard. - [Agent Evidence: SIEM and Detection Integration](https://pipelab.org/learn/agent-evidence-detection-integration/): Pipelock action receipts integrate with SIEM, audit, and LLM detection pipelines. Tamper-evident JSONL, hash-chained, Ed25519-signed. - [AI Agent Data Redaction](https://pipelab.org/learn/ai-agent-data-redaction/): Pipelock redacts AI agent secrets in flight using class-preserving placeholders across Anthropic, OpenAI, Gemini, and custom JSON providers. - [Pipelock v2.3 Upgrade Guide](https://pipelab.org/learn/pipelock-v230-upgrade/): Pipelock v2.3 upgrade guide: drop-in upgrade from v2.2.x, plus how to enable class-preserving redaction and generic SSE streaming scanning. - [SSE Streaming Response Scanning](https://pipelab.org/learn/sse-streaming-response-scanning/): Pipelock v2.3.0 streams every SSE response with per-event DLP and prompt injection scanning. OpenAI, Anthropic, Kilo Gateway, any LLM SSE. - [LLM Security: A Practitioner's Guide to Protecting Large Language Models and AI Agents](https://pipelab.org/learn/llm-security/): LLM security covers prompt injection, data leaks, tool poisoning, and agent runtime attacks. Practitioner guide to threats and where defenses fit. - [AI Agent Data Loss Prevention: How DLP Works for Agents (and Where It Breaks)](https://pipelab.org/learn/ai-agent-data-loss-prevention/): AI agent DLP guide: where agents leak credentials and PII, what catches it at the network layer, and the open-source self-hosted approach. - [Chatbot Security: Risks, Defenses, and Where Network Controls Fit](https://pipelab.org/learn/chatbot-security/): Chatbot security guide: credential leaks, prompt injection, jailbreaks, oversharing, and the network-layer controls that catch what the model misses. - [What Is MCP? Model Context Protocol Explained for AI Agents](https://pipelab.org/learn/what-is-mcp/): Plain-language guide to Model Context Protocol (MCP): what it is, who built it, how it works, and how it differs from function calling and RAG. - [Mediation Envelope Signing and Inbound Verification](https://pipelab.org/learn/mediation-envelope-signing/): Pipelock mediation envelope guide: RFC 9421 signing, inbound verification, SPIFFE actors, and the well-known directory for cross-org federation. - [Pipelock Kubernetes Companion Proxy](https://pipelab.org/learn/pipelock-kubernetes-companion-proxy/): Pipelock Kubernetes companion proxy guide: generate an enforced proxy Deployment, Service, NetworkPolicies, and bound identity from a workload manifest. - [Pipelock Posture Verify Guide](https://pipelab.org/learn/pipelock-posture-verify/): Pipelock posture verify guide: validate signed posture capsules, enforce policy thresholds, and use exit codes separating integrity from policy failures. - [Pipelock Session Recovery](https://pipelab.org/learn/pipelock-session-recovery/): Pipelock session recovery guide: use inspect, explain, release, terminate, and recover to handle airlocked sessions without guessing at proxy state. - [Pipelock v2.2 Upgrade Guide](https://pipelab.org/learn/pipelock-v220-upgrade/): Pipelock v2.2 upgrade guide: strict YAML validation, rollout checks, and the operator steps to verify config before you cut traffic over. - [AI Runtime Security: Defending AI Agents and Models at Execution Time](https://pipelab.org/learn/ai-runtime-security/): AI runtime security covers model, agent, and infrastructure threats at execution time: prompt injection, tool misuse, egress exfiltration, and defenses. - [Generative AI Firewall: What It Is and When You Need One](https://pipelab.org/learn/generative-ai-firewall/): Generative AI firewall guide to prompt filtering, output scanning, agent egress control, vendors, and where open-source tools fit. - [Cloudflare Sandboxes and Pipelock: Two-Layer Egress Control for AI Agents](https://pipelab.org/learn/cloudflare-sandboxes-pipelock/): Cloudflare Sandboxes provides agent isolation and domain filtering. Pipelock adds content scanning for credentials, injection, and tool poisoning. - [The Mythos-Ready Playbook: Runtime Controls for the AI Vulnerability Storm](https://pipelab.org/learn/mythos-ready-playbook/): CSA/SANS/OWASP Mythos-Ready playbook mapped to runtime controls: egress filtering, agent containment, and machine-speed response. - [MCP Authorization: Access Control for AI Agent Tool Calls](https://pipelab.org/learn/mcp-authorization/): MCP authorization controls which agents access which tools. Covers OAuth 2.1, scopes, tool-level RBAC, confused deputy, and audit patterns. - [OWASP MCP Top 10 (MCP01:2025 through MCP10:2025): Risks and Practical Defenses](https://pipelab.org/learn/owasp-mcp-top10/): OWASP MCP Top 10 (MCP01:2025-MCP10:2025): each risk category explained with the scanner, gateway, inspection, and audit controls that stop it. - [Shadow MCP: Find and Lock Down Rogue MCP Servers](https://pipelab.org/learn/shadow-mcp/): Shadow MCP is the unauthorized MCP connectivity hiding in your codebase. How to find rogue MCP servers, score the risk, and enforce policy at runtime. - [AI Agent Security Best Practices: A Practical Checklist](https://pipelab.org/learn/ai-agent-security-best-practices/): AI agent security best practices start with least privilege, network isolation, and runtime inspection. Use this checklist to lock down your agents. - [AI Agent Security Tools: Scanners, Firewalls, and Gateways](https://pipelab.org/learn/ai-agent-security-tools/): AI agent security tools range from static scanners to runtime firewalls. Compare what each layer catches and pick the right stack for your agents. - [AI Agent Compliance: Audit Logs, Policy, and Evidence](https://pipelab.org/learn/ai-agent-compliance/): AI agent compliance needs audit logs, runtime policy controls, and signed evidence. Map agent behavior to SOC 2, EU AI Act, and OWASP frameworks. - [AI Egress Proxy: Control What Your Agents Send](https://pipelab.org/learn/ai-egress-proxy/): An AI egress proxy routes all agent traffic through one control point. Inspect HTTP and MCP requests, block data leaks, and enforce network policy. - [MCP Gateway Open Source vs Commercial: Comparison and How to Choose](https://pipelab.org/learn/mcp-gateway/): MCP gateway guide comparing open source and commercial options, routing, auth, content inspection, proxy differences, and security controls. - [MCP Security Tools: Scanners, Proxies, and Gateways](https://pipelab.org/learn/mcp-security-tools/): MCP security tools help you scan servers, inspect traffic, block tool poisoning, and control access. Compare the main options and their trade-offs. - [Open Source AI Firewall: Self-Hosted Agent Security](https://pipelab.org/learn/open-source-ai-firewall/): Open source AI firewall comparison for self-hosted agent security: Pipelock, LlamaFirewall, MCP gateways, guardrails, and runtime controls. - [Secure AI Agent Deployment: Pre-Launch to Production](https://pipelab.org/learn/secure-ai-agent-deployment/): Secure AI agent deployment starts before launch. Isolate credentials, restrict network access, inspect tool traffic, and log every decision. - [Pipelock Action Receipt Format (Implementation Spec)](https://pipelab.org/learn/action-receipt-spec/): Pipelock signed receipt formats: Ed25519 ActionReceipt v1 for proxy decisions, plus EvidenceReceipt v2 for v2.4 contract lifecycle and shadow evidence. - [AI Agent Security: Three Layers You Actually Need](https://pipelab.org/learn/ai-agent-security/): AI agent security explained in three layers: agent-side hooks, inference guardrails, and egress inspection. What each layer catches and what it misses. - [LLM Prompt Injection: What It Is and Why It Matters for AI Agents](https://pipelab.org/learn/llm-prompt-injection/): LLM prompt injection explained. How attackers hijack AI agents through malicious text in tool responses, web pages, and MCP servers. Defenses included. - [MCP Proxy: How It Scans MCP Traffic Bidirectionally](https://pipelab.org/learn/mcp-proxy/): An MCP proxy sits between agents and servers, inspecting tool descriptions, arguments, and responses for injection, credentials, and rug-pulls. - [MCP Tool Poisoning: Detection and Runtime Defense](https://pipelab.org/learn/mcp-tool-poisoning/): MCP tool poisoning hides malicious instructions in tool metadata. Catch rug-pulls and block unsafe tool changes at runtime with proxy-layer defense. - [MCP Vulnerabilities: Known Risks and Defenses](https://pipelab.org/learn/mcp-vulnerabilities/): MCP vulnerabilities mapped: tool poisoning, rug-pulls, credential theft, SSRF, prompt injection, session hijacking. Runtime defenses for each risk. - [Prompt Injection Detection: Techniques and Tools](https://pipelab.org/learn/prompt-injection-detection/): Prompt injection detection techniques for AI agents. Pattern matching, ML classifiers, normalization pipelines, and how to combine detection layers. - [MCP Server Security: Seven Attacks, Seven Defenses](https://pipelab.org/learn/how-to-secure-mcp/): MCP server security starts with auth, tool controls, and runtime inspection. Seven common attacks and the defenses that stop each one. - [AI Compliance Evidence: Signed Reports](https://pipelab.org/learn/compliance-evidence/): AI compliance evidence from Pipelock. Maps runtime controls to five frameworks and generates signed bundles. SARIF integrates with GitHub Code Scanning. - [Canary Tokens: Synthetic Secret Detection](https://pipelab.org/learn/canary-tokens/): Canary tokens for AI agent security. Plant synthetic secrets in Pipelock that trigger alerts when an agent attempts to exfiltrate them. - [Flight Recorder: AI Agent Audit Log](https://pipelab.org/learn/flight-recorder/): AI agent audit log with hash-chained, tamper-evident entries. Pipelock's flight recorder writes DLP-redacted JSONL with Ed25519 signed checkpoints. - [JetBrains MCP Security: Scanning with Pipelock](https://pipelab.org/learn/jetbrains-integration/): JetBrains MCP security guide. Install Pipelock to scan MCP connections in IntelliJ IDEA, PyCharm, WebStorm, GoLand, and Junie agents. - [OWASP AIVSS: Pipelock Agent Risk Coverage](https://pipelab.org/learn/owasp-aivss-coverage/): Pipelock maps controls to all 10 OWASP AIVSS agentic AI risk categories, supporting assessments that reduce vulnerability scores by up to 33%. - [Pipelock Detection Rules: Community Collection](https://pipelab.org/learn/community-rules/): Pipelock detection rules from the community. 28 signed rules covering DLP patterns, MCP tool poisoning, and prompt injection scanning. - [SlowMist MCP Security: Pipelock Coverage](https://pipelab.org/learn/slowmist-mcp-security-coverage/): Pipelock covers 10 of 19 SlowMist MCP security test cases fully, 8 partially, with 1 out of scope. Full item-by-item breakdown. - [VS Code MCP Security: Scanning with Pipelock](https://pipelab.org/learn/vscode-integration/): VS Code MCP security guide. Install Pipelock to scan MCP server traffic for credential leaks, prompt injection, and tool poisoning before execution. - [Pipelock Hooks for Claude Code: Setup Guide](https://pipelab.org/learn/claude-code-hooks/): Install Pipelock hooks for Claude Code in one command. Scans Bash, WebFetch, Write, Edit, and MCP tool calls for credential leaks and injection. - [OWASP Agentic AI Threats: Pipelock Coverage](https://pipelab.org/learn/owasp-agentic-threats/): Pipelock covers 12 of 15 OWASP Agentic AI threats including memory poisoning, tool misuse, privilege compromise, and rogue agents. Full coverage mapping. - [OWASP Agentic Top 10: Pipelock Coverage](https://pipelab.org/learn/owasp-agentic-top10/): Pipelock coverage for all 10 risks in the OWASP Top 10 for Agentic Applications 2026 (ASI01-ASI10), with per-threat assessment. - [OWASP LLM Top 10: Pipelock Coverage](https://pipelab.org/learn/owasp-llm-top10/): Pipelock covers 7 of 10 OWASP LLM Top 10 threats at the network layer: prompt injection, sensitive info disclosure, excessive agency, and supply chain. - [EU AI Act Compliance: Article 26 Deployer Obligations and 6-Month Log Retention](https://pipelab.org/learn/eu-ai-act-compliance/): EU AI Act compliance for AI agents: Article 26 deployer duties, the 26(6) six-month log retention rule, and the runtime controls that satisfy them. - [Cursor AI Security: Scanning Hooks with Pipelock](https://pipelab.org/learn/cursor-integration/): Cursor AI security guide. Install Pipelock hooks to block credential exfiltration, reverse shells, and dangerous commands before they execute. - [How to Secure AI Agents: Preventing Credential Leaks](https://pipelab.org/learn/agent-egress-security/): Agent egress security controls outbound AI agent traffic to stop credential leaks via HTTP, DNS, and MCP. Attack vectors and runtime defenses. - [MCP Security: Risks, Best Practices, and Runtime Defenses](https://pipelab.org/learn/mcp-security/): MCP security guide to risks, best practices, OWASP controls, tool poisoning, secret leaks, SSRF, runtime defenses, and audit. - [Prompt Injection Prevention at the Network Layer](https://pipelab.org/learn/prompt-injection-network-defense/): Prompt injection prevention beyond the model layer. Network scanning catches injection in HTTP and MCP traffic before it reaches the AI agent.