Show HN: AgentShield Zero-dep secret redactor and shell firewall for Claude RitualDev-Lab released AgentShield, a zero-runtime-dependency tool that intercepts shell commands and stdout/stderr from autonomous coding agents such as Claude Code, Cursor and Windsurf to block reads of `.env` files, `printenv` environment dumps and other credential leaks before they reach third-party model APIs or git history. AgentShield reports under 20 µs P99 redaction across 10,000-call benchmarks at more than 149,000 ops/sec, and ships a command firewall that catches obfuscated variants like `cat .e""nv`, `/proc/self/environ` and inline `node`/`python` env dumps, plus OS sandbox preflight for macOS Seatbelt, Linux bwrap/Landlock and Windows AppContainer. The project's THREAT_MODEL.md states that userland command inspection is defense-in-depth against accidental exfiltration and common script bypasses, not an OS kernel security boundary. Stop Claude Code, Cursor, Windsurf, and autonomous coding agents from leaking .env secrets, SSH keys, or running destructive shell commands. Zero runtime dependencies. 100% local & air-gapped by default. <20 µs P99 redaction across 10,000-call benchmarks 149k+ ops/sec . npx @ritualdev-lab/agentshield demo bash $ npx @ritualdev-lab/agentshield exec "cat .env && printenv" AgentShield BLOCKED: Direct credential file read & environment dump .env / printenv $ node print-config.js | npx @ritualdev-lab/agentshield stream {"db":" AGENT SHIELD:DATABASE URL:9f3a12 ","token":" AGENT SHIELD:GITHUB TOKEN:4c8e19 "} Want to record a fresh 15-second terminal GIF? Run vhs assets/demo.tape https://github.com/RitualDev-Lab/AgentShield/blob/main/assets/demo.tape with Charm VHS https://github.com/charmbracelet/vhs . Autonomous coding agents have direct access to your shell, filesystem, and git repo. Even well-behaved agents routinely run cat .env , printenv , node -e 'console.log process.env ' , or commit live test keys into PRs—leaking raw credentials into third-party model APIs and git history. AgentShield intercepts commands and stdout/stderr before credentials leave your machine: - Obfuscation-resistant command firewall : Catches cat .e""nv , cat .e?v , /proc/self/environ , base64 / xxd , tar / cp , and inline node / python env dumps. - Boundary-safe streaming redactor : Catches secrets split across arbitrary 1-byte TCP/stdio chunks and multiline PEM blocks 0 runtime dependencies, linear-time regex + Shannon entropy . - OS sandbox preflight & profiles : Generates and verifies macOS Seatbelt sandbox-exec , Linux bwrap /Landlock, and Windows AppContainer isolation via agentshield doctor . - Unified 3-layer stack : Boot AgentShield + DBShield https://github.com/RitualDev-Lab/DBShield + SkillPrism https://github.com/RitualDev-Lab/SkillPrism from a single declarative ritual.policy.yaml https://github.com/RitualDev-Lab/AgentShield/blob/main/examples/ritual.policy.yaml via agentshield up . Think you can bypass our .env / /proc/self/environ blocker or split a secret across stream chunks without triggering redaction? npx @ritualdev-lab/agentshield bounty-verify "your-payload-here" If you find a bypass, open an issue with your repro—every confirmed bypass gets a regression test and credit in the repo. Check THREAT MODEL.md https://github.com/RitualDev-Lab/AgentShield/blob/main/THREAT MODEL.md for exact scope and honest OS isolation limits. Quick Start -instant-30-second-setup · Full Guide https://github.com/RitualDev-Lab/AgentShield/blob/main/GUIDE.md · Threat Model https://github.com/RitualDev-Lab/AgentShield/blob/main/THREAT MODEL.md · Examples Claude Code, LangGraph, E2B/Daytona https://github.com/RitualDev-Lab/AgentShield/blob/main/examples · GitHub Action -3-cicd-security-gate--github-action 1. Diagnose your OS sandbox Seatbelt / bwrap / Landlock / AppContainer npx @ritualdev-lab/agentshield doctor 2. Install a git pre-commit secret leak gate npx @ritualdev-lab/agentshield hook install 3. Generate Claude Code PreToolUse or Cursor hooks npx @ritualdev-lab/agentshield init-claude npx @ritualdev-lab/agentshield init-cursor 4. Wrap any agent shell command safely npx @ritualdev-lab/agentshield exec "cat .env" Intercept and sandbox agent terminal execution. If an agent tries to read .env , dump shell variables printenv , or send keys to outbound endpoints, AgentShield blocks it on the fly: npx @ritualdev-lab/agentshield exec "cat .env" 🚨 AgentShield Sandbox Block Blocked attempt to read raw .env or private credential file. Protected credentials from entering agent LLM context window Important Defense-in-Depth vs OS Security Boundary : Userland command inspection AST parsing and regex heuristics is defense-in-depth designed to prevent accidental exfiltration and common script bypasses. It is not an OS kernel security boundary. Arbitrary compiled binaries or direct kernel syscalls require true OS-level containerization. | Platform | Primary Isolation Mechanism | Security Boundary Level | Guarantees & Limitations | |---|---|---|---| | macOS | macos sandbox exec | Kernel-Enforced | System call mediation via Apple Seatbelt; restricts file read/write and networking outside workspace. | | Linux | linux landlock / bwrap | Defense-in-Depth unless containerized | Generates Landlock LSM & bubblewrap profiles. Without a container runtime, Node child processes inherit caller privileges. | | Windows | windows appcontainer | Defense-in-Depth | Generates AppContainer / Low-Integrity profile templates. Win32 child processes run with normal caller token integrity. | | Fallback | process level firewall | Defense-in-Depth | AST pattern firewall and real-time streaming redaction. | By default, requesting kernel sandboxing on non-macOS hosts logs an isolation warning and runs under the defense-in-depth AST firewall. To fail-closed and refuse execution whenever OS-level kernel isolation cannot be guaranteed: Refuse execution if the host cannot enforce true OS kernel isolation npx @ritualdev-lab/agentshield exec "npm test" --require-isolation 🛑 AgentShield Isolation Refusal Execution refused: requireIsolation is enabled, but OS-level kernel isolation is unavailable on host win32 . Refusing to silently downgrade to process-level firewall. In the TypeScript SDK: js const result = await interceptor.execute command, { enableKernelSandbox: true, requireIsolation: true, // Fails closed instead of silently downgrading } ; Catch leaked credentials before they enter git history. Audits staged diffs automatically: Install once in your repo native git hook npx @ritualdev-lab/agentshield hook git-install Or manually audit staged files npx @ritualdev-lab/agentshield hook check Or using the standard pre-commit https://pre-commit.com/ framework .pre-commit-config.yaml : repos: - repo: https://github.com/RitualDev-Lab/AgentShield rev: v0.1.1 hooks: - id: agentshield - id: agentshield-audit Block pull requests that introduce exposed credentials into your codebase: name: AgentShield Security Gate on: pull request, push jobs: secret-audit: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 with: fetch-depth: 0 - uses: RitualDev-Lab/AgentShield@v1 with: fail on leak: "true" Or run via CLI in any CI container: npx @ritualdev-lab/agentshield ci --base origin/main --report security-report.md Assess files and workspace streams against technical secret-handling controls in standard frameworks SOC 2, PCI-DSS, HIPAA, ISO 27001 : npx @ritualdev-lab/agentshield compliance .env 📋 SECRET-CONTROL ASSESSMENT Status: NO FINDINGS IN ASSESSED CONTROLS Assessed Controls Score: 100% ℹ️ Scope: Technical secret detection, real-time streaming token redaction, and CLI command firewall. ⚠️ Disclaimer: Notice: This report reflects only the results of automated secret detection across assessed technical controls 'NO FINDINGS IN ASSESSED CONTROLS' . It does NOT establish overall organizational SOC 2, HIPAA, PCI-DSS, or ISO 27001 compliance. Overall compliance requires an accredited third-party audit firm, administrative governance, physical safeguards, and operational policies. Assessed Controls: ✅ SOC2 CC6.1: Logical Access Controls & Credential Integrity ✅ SOC2 CC6.6: Boundary Protection & Unauthorized Egress Controls ✅ PCI DSS Req-3.4: Protection of Authentication & Payment Gateway Secrets ✅ PCI DSS Req-8.3: Strong Authentication Credential Management ✅ HIPAA §164.312 a 1 : Technical Safeguards - Access Control & Authentication ✅ ISO27001 A.8.28: Secure Coding & Secret Management ✅ ISO27001 A.8.24: Use of Cryptography & Key Protection Broader Controls Not Assessed by Secret Scanning : ⏸️ SOC2 CC1.1: Integrity & Ethical Values Governance NOT ASSESSED ⏸️ SOC2 CC5.2: Risk Assessment & Vendor Management NOT ASSESSED ⏸️ PCI DSS Req-9.1: Physical Access Restrictions NOT ASSESSED ⏸️ HIPAA §164.308 a 1 : Administrative Safeguards NOT ASSESSED ⏸️ ISO27001 A.5.1: Policies for Information Security NOT ASSESSED Instead of cleartext .env keys, AgentShield provides deterministic, collision-resistant surrogate tokens AGENT SHIELD:ID:hexHash . Agents can safely manipulate configurations and inspect outputs without ever seeing the plaintext secret in prompt history, rehydrating values locally when required. AgentShield provides 1-command generators for leading AI coding agent environments: Automatically intercept agent terminal executions before commands touch your environment: npx @ritualdev-lab/agentshield init-claude Generates .claude/settings.json configured with: { "hooks": { "PreToolUse": { "matcher": "Bash|Terminal", "command": "npx @ritualdev-lab/agentshield exec --claude-hook" } } } Note: Claude Code delivers tool call payloads via stdin JSON. AgentShield inspects the payload in real-time and cleanly returns exit code 2 to halt unauthorized commands before execution. npx @ritualdev-lab/agentshield init-cursor Generates .cursor/rules.json with sensitive path boundaries .env , .pem , id rsa and pre-execution command sandboxing. Plug SKILL.md https://github.com/RitualDev-Lab/AgentShield/blob/main/SKILL.md into workspace agent instructions to enforce zero-leak guarantees natively. Traditional scanners gitleaks , trufflehog were designed for post-facto static git repository scanning scanning files and commit histories at rest . AgentShield is designed specifically for Autonomous Agent Runtime Protection — intercepting shell commands, scrubbing streaming stdio chunk-by-chunk in sub-milliseconds, and sanitizing LLM prompt inputs before transmission. | Feature / Metric | AgentShield | GitLeaks | TruffleHog | |---|---|---|---| | Primary Domain | Agent Runtime & Stdio Interception | Git History Scanner | Git & Filesystem Scanner | | Average Scan Latency | < 0.04 ms / scan | ~ 2 - 5 ms | ~ 10 - 50 ms | | Throughput | 28,000+ operations/sec | ~ 5,000 ops/sec | ~ 1,200 ops/sec | | Streaming Stdio Interception | ✅ Native createRedactingStream | ❌ Disk / Git diff only | ❌ Disk / Git diff only | | Agent AST Command Sandbox | ✅ Native exec / run | ❌ None | ❌ None | | Deterministic Vault Rehydration | ✅ Native AGENT SHIELD:... | ❌ None | ❌ None | | MCP Protocol Filter JSON-RPC | ✅ Native mcp-proxy | ❌ None | ❌ None | | Zero Runtime Dependencies | ✅ 0 deps Pure Node.js | Go binary | Go binary / Python | | Git Pre-Commit & CI Gates | ✅ Built-in | ✅ Built-in | ✅ Built-in | AgentShield combines high-performance regular expressions with Shannon Entropy to catch both structured keys and arbitrary high-entropy passwords: - 🤖 AI Providers : OpenAI sk-proj- , Anthropic Claude sk-ant- , Google Gemini AIzaSy , Hugging Face hf - ☁️ Cloud Infrastructure : AWS Access Key ID AKIA , AWS Secret Access Keys - 💳 Payments & SaaS : Stripe Live sk live , Slack Incoming Webhooks - 🐙 Version Control : GitHub Personal Access Tokens ghp , github pat - 🔐 Cryptography : PEM / OpenSSH private key blocks, JSON Web Tokens JWT - 📊 Mathematical Entropy : High-entropy password detection with false-positive filtering AgentShield provides first-class, idiomatic SDKs across multiple languages: | Language / Platform | Package / Location | Supported Runtimes & Frameworks | Integration Pattern | |---|---|---|---| | Node.js / TypeScript | @ritualdev-lab/agentshield | Node 20+, Cursor, Claude Code, MCP | In-process native TypeScript | | Python | agentshield sdks/python | Python 3.9+, LangChain, LangGraph, CrewAI, AutoGen | In-process standalone + Sidecar | | Go | sdks/go | Go 1.21+, net/http middleware, Gin, Chi | JSON-RPC 2.0 Stdio Sidecar | | Rust | sdks/rust | Rust 2021 edition | JSON-RPC 2.0 Stdio Sidecar | | Any Language / Shell | agentshield sidecar | Ruby, Elixir, PHP, C++, Bash | Stdio Line-Delimited JSON-RPC 2.0 | Works in pure-Python without requiring Node.js, with built-in LangChain/LangGraph callbacks: python from agentshield import AgentShieldEngine, AgentShieldCallbackHandler from langchain openai import ChatOpenAI shield = AgentShieldEngine redacted = shield.scan and redact "Query database with sk-proj-placeholder-token" print redacted "sanitizedText" "Query database with AGENT SHIELD:AI:7b3a4f1c " Attach to LangChain to protect prompt inputs automatically: llm = ChatOpenAI callbacks= AgentShieldCallbackHandler import "github.com/RitualDev-Lab/agentshield/sdks/go" client, := agentshield.NewClient ctx defer client.Close res, := client.ScanAndRedact ctx, "Stripe secret sk live placeholder token" fmt.Println res.SanitizedText js use agentshield::AgentShieldClient; let client = AgentShieldClient::new ?; let res = client.scan and redact "My token is ghp placeholder token" ?; println "Sanitized: {}", res.sanitized text ; Any language can interact with AgentShield via line-delimited JSON-RPC 2.0: npx @ritualdev-lab/agentshield sidecar {"jsonrpc": "2.0", "id": 1, "method": "shield.scanAndRedact", "params": {"text": "My API key is sk-proj-placeholder"}} Response: {"jsonrpc":"2.0","id":1,"result":{"hasSecrets":true,"sanitizedText":"My API key is AGENT SHIELD:AI:... ","findings": ... }} Integrate AgentShield directly into your AI workflows, proxy servers, or custom agent frameworks: js import { AgentShieldEngine, AgentCommandSandbox, AgentStdioInterceptor } from "@ritualdev-lab/agentshield"; const shield = new AgentShieldEngine ; // Scan and redact unmasked credentials from LLM prompt inputs const rawPrompt = Run tests with OPENAI API KEY=${mySecretToken} ; const result = shield.scanAndRedact rawPrompt ; console.log result.hasSecrets ; // true console.log result.sanitizedText ; // "Run tests with OPENAI API KEY= AGENT SHIELD:OPENAI API KEY:c2stcH " // Deterministically rehydrate when receiving LLM response back locally const original = shield.rehydrate result.sanitizedText ; - Live Documentation : https://agentshield.ritualdev.in/ https://agentshield.ritualdev.in/ - Bug Bounty Program : Read our SECURITY.md https://github.com/RitualDev-Lab/AgentShield/blob/main/SECURITY.md for rewards $50 – $500 . - Open Governance Charter : Read our GOVERNANCE.md https://github.com/RitualDev-Lab/AgentShield/blob/main/GOVERNANCE.md for project stewardship. - Grant Applications : Review our GRANTS.md https://github.com/RitualDev-Lab/AgentShield/blob/main/GRANTS.md dossier for NLnet, OpenSSF & Mozilla. - Contributing : Check out CONTRIBUTING.md https://github.com/RitualDev-Lab/AgentShield/blob/main/CONTRIBUTING.md to add new secret patterns. AgentShield is initiated and maintained by the team at RitualDev Lab https://github.com/RitualDev-Lab and protected by the global AI security research community. |