io.github.Tyox-all/mund
AI security scanner - secrets, PII, prompt injection, and exfiltration detection.
Ask AI about io.github.Tyox-all/mund
Powered by Claude Β· Grounded in docs
I know everything about io.github.Tyox-all/mund. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
πΈοΈ Weave Protocol
Enterprise Security Suite for AI Agents
A TypeScript monorepo providing security, encryption, compliance, and governance tools for AI agent systems. Built for the Model Context Protocol (MCP) ecosystem.
π What's New
π Tollere v0.2.2 β Multi-Channel Supply Chain Security
Old English
tollereβ the customs inspector who stood at the gate and examined every good crossing the boundary.
Catches typosquats, CVEs, compromised maintainers, Docker tag overwriting, IDE extension impersonation, and sandwich-pattern attacks before the install completes. Validated against the real-world Checkmarx KICS supply chain compromise (April 2026) β Tollere catches the v2.1.20 tag reassignment in real-time.
npx @weave_protocol/tollere scan # scan package.json
npx @weave_protocol/tollere docker checkmarx/kics:v2.1.20 # π Docker images
npx @weave_protocol/tollere ext ms-python.python vscode # π IDE extensions
npx @weave_protocol/tollere sandwich some-package # π sandwich pattern
Coverage: npm, PyPI, Cargo, Go, Maven, Docker Hub, VS Code Marketplace (covers Cursor + Windsurf), Open VSX (VSCodium/Gitpod), JetBrains Marketplace (IntelliJ/PyCharm/WebStorm/etc).
π Web Dashboard for Monitoring (API v1.0.12)
Real-time security monitoring UI bundled with the API package:
npx @weave_protocol/api
# β Open http://localhost:3000/dashboard
Live activity feed, threat intel status, compliance frameworks, MCP server reputation. See API README β
π Python/LlamaIndex Integration (v0.1.0)
Security scanning for LlamaIndex applications:
from weave_protocol_llamaindex import WeaveSecurityHandler
from llama_index.core.callbacks import CallbackManager
from llama_index.core import Settings
Settings.callback_manager = CallbackManager([WeaveSecurityHandler()])
# All LlamaIndex operations now scanned - threats auto-blocked
π LangChain.js Integration (v1.0.1)
Drop-in security for LangChain.js applications:
import { WeaveSecurityCallback } from '@weave_protocol/langchain';
const chain = new LLMChain({
llm: new ChatOpenAI(),
prompt,
callbacks: [new WeaveSecurityCallback({ action: 'block' })],
});
π¦ Packages
| Package | Version | Description |
|---|---|---|
| π‘οΈ @weave_protocol/mund | 0.2.2 | Security scanner - secrets, PII, injection, MCP vetting, threat intel |
| ποΈ @weave_protocol/hord | 0.1.6 | Encrypted vault with Yoxallismus cipher |
| βοΈ @weave_protocol/domere | 1.3.4 | Compliance (PCI-DSS, ISO27001, SOC2, HIPAA, GDPR, CCPA) & verification |
| π₯ @weave_protocol/witan | 1.0.2 | Multi-agent consensus & governance |
| π @weave_protocol/hundredmen | 1.0.6 | Real-time MCP proxy - intercept, scan, gate tool calls |
| π @weave_protocol/tollere | 0.2.2 | Supply chain security - npm, Docker images, IDE extensions, sandwich pattern detection |
| π @weave_protocol/langchain | 1.0.1 | LangChain.js security callbacks & tool wrappers |
| π weave-protocol-llamaindex | 0.1.0 | Python/LlamaIndex security callbacks & tools |
| π @weave_protocol/api | 1.0.12 | REST API for all packages + dashboard |
π€ AI Agent Skills
Each package includes a SKILL.md file following the Claude Agent Skills specification. These teach AI agents how to use Weave Protocol tools effectively.
| Package | Skill Name | Triggers |
|---|---|---|
| π‘οΈ Mund | security-scanning | scan, detect secrets, check injection, vet MCP server, threat intel |
| ποΈ Hord | encrypting-data | encrypt, decrypt, vault, Yoxallismus, protect |
| βοΈ Domere | compliance-auditing | audit, checkpoint, SOC2, HIPAA, PCI-DSS, GDPR, CCPA, blockchain |
| π₯ Witan | consensus-governance | consensus, vote, approve, policy, escalate |
| π Hundredmen | security-inspection | intercept, drift, reputation, approve, block, live feed |
| π Tollere | supply-chain-security | npm install, docker pull, install extension, dependency check, typosquat, CVE, sandwich pattern |
| π Langchain | langchain-security | LangChain, callback, secure tool, RAG security, PII redaction |
| π API | weave-api-calling | REST API, HTTP endpoint, curl, fetch |
Installation:
git clone https://github.com/Tyox-all/Weave_Protocol.git
mkdir -p ~/.claude/skills/weave-protocol
cp Weave_Protocol/*/SKILL.md ~/.claude/skills/weave-protocol/
Once installed, Claude automatically invokes the appropriate skill for each task.
π Quick Start
Install All Packages
npm install @weave_protocol/mund @weave_protocol/hord @weave_protocol/domere @weave_protocol/hundredmen @weave_protocol/tollere @weave_protocol/langchain
Claude Desktop Integration
Add to claude_desktop_config.json:
{
"mcpServers": {
"mund": { "command": "npx", "args": ["-y", "@weave_protocol/mund"] },
"hord": { "command": "npx", "args": ["-y", "@weave_protocol/hord"] },
"domere": { "command": "npx", "args": ["-y", "@weave_protocol/domere"] },
"hundredmen": { "command": "npx", "args": ["-y", "@weave_protocol/hundredmen"] },
"tollere": { "command": "npx", "args": ["-y", "@weave_protocol/tollere"] }
}
}
β¨ Package Details
π‘οΈ Mund β The Guardian
Real-time security scanning for AI agents.
| Category | Features |
|---|---|
| Secrets | API keys, tokens, passwords, certificates (30+ patterns) |
| PII | SSN, credit cards, emails, phone numbers, addresses |
| Injection | Prompt injection, jailbreak attempts, instruction override |
| Code | Dangerous patterns, eval/exec, SQL injection, XSS |
| MCP Servers | Malicious tool descriptions, typosquatting, dangerous permissions |
| Threat Intel | MITRE ATT&CK patterns, community feeds, auto-updates |
π Skill: security-scanning
ποΈ Hord β The Vault
Encrypted storage with the Yoxallismus dual-tumbler cipher.
| Category | Features |
|---|---|
| Encryption | AES-256-GCM, ChaCha20-Poly1305 |
| Key Derivation | Argon2id with configurable parameters |
| Yoxallismus | Dual-layer tumbler/deadbolt obfuscation |
| Memory Safety | Secure buffer handling, auto-zeroing |
π Skill: encrypting-data
βοΈ Domere β The Judge
Enterprise-grade verification, orchestration, compliance, and audit infrastructure.
| Category | Features |
|---|---|
| Verification | Intent tracking, drift detection, execution replay |
| Compliance | SOC2, HIPAA, PCI-DSS, ISO27001, GDPR, CCPA |
| Blockchain | Solana & Ethereum anchoring for immutable audit trails |
Blockchain Anchoring:
- Solana Mainnet:
6g7raTAHU2h331VKtfVtkS5pmuvR8vMYwjGsZF1CUj2o - Solana Devnet:
BeCYVJYfbUu3k2TPGmh9VoGWeJwzm2hg2NdtnvbdBNCj - Ethereum:
0xAA8b52adD3CEce6269d14C6335a79df451543820
π Skill: compliance-auditing
π₯ Witan β The Council
Multi-agent consensus and governance.
| Category | Features |
|---|---|
| Consensus | Unanimous, majority, weighted, quorum protocols |
| Policy | Rule enforcement, permission management, escalation |
| Communication | Agent bus, broadcast, point-to-point messaging |
π Skill: consensus-governance
π Hundredmen β The Watchers
Real-time MCP security proxy that intercepts, scans, and gates AI agent tool calls.
| Category | Features |
|---|---|
| Interception | Proxy all MCP tool calls in real-time |
| Drift Detection | "Said X, doing Y" - catch unauthorized actions |
| Reputation | Server trust scores, community reports |
| Manual Gates | Require approval for high-risk operations |
π Skill: security-inspection
π Tollere β The Customs Inspector
Supply chain security for AI-generated code. Catches malicious packages, Docker images, and IDE extensions before they reach node_modules/, your container, or your editor.
| Surface | Coverage |
|---|---|
| Packages | npm, PyPI, Cargo, Go, Maven (typosquats, CVEs, maintainer reputation) |
| π Sandwich Pattern | Malicious code hidden between a clean "filling" version (Checkmarx attack pattern) |
| π Docker Images | Tag overwrite detection, phantom tags (Docker Hub) |
| π IDE Extensions | VS Code (Cursor, Windsurf), Open VSX (VSCodium, Gitpod), JetBrains (IntelliJ, PyCharm, WebStorm, etc.) |
npx @weave_protocol/tollere scan
npx @weave_protocol/tollere docker checkmarx/kics:v2.1.20
npx @weave_protocol/tollere ext ms-python.python vscode
π Skill: supply-chain-security
π Langchain β The Bridge
Security integration for LangChain.js applications.
| Category | Features |
|---|---|
| Callbacks | Drop-in WeaveSecurityCallback for any chain/agent |
| Tool Wrappers | Wrap tools with threat scanning and approval gates |
| Retrievers | Scan RAG documents, auto-redact PII |
π Skill: langchain-security
ποΈ Architecture
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β AI Agent System β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ€
β β
β ββββββββββββ ββββββββββββ ββββββββββββ ββββββββββββ β
β β π‘οΈ Mund β β ποΈ Hord β β βοΈ Domereβ β π₯ Witan β β
β β Guardian β β Vault β β Judge β β Council β β
β ββββββ¬ββββββ ββββββ¬ββββββ ββββββ¬ββββββ ββββββ¬ββββββ β
β β β β β β
β Security Encryption Compliance Consensus β
β β β β β β
β βββββββββββββββ΄ββββββββββββββ΄ββββββββββββββ β
β β β
β ββββββββββββββββ ββββββββ΄βββββββ ββββββββββββββββ β
β βπ Hundredmen β β π Tollere β β π API β β
β β Watchers β β Customs β β REST + UI β β
β ββββββββββββββββ βββββββββββββββ ββββββββββββββββ β
β β β β β
β Runtime Calls Supply Chain Universal Access β
β β β β β
β ββββββββββββββββββββ΄βββββββββββββββββββ β
β β β
β ββββββββ΄ββββββββ β
β β π Langchain β β
β β Bridge β β
β ββββββββββββββββ β
β β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
π Security Model
Defense-in-depth across the entire AI agent lifecycle:
- π Tollere inspects every dependency, image, and extension before it enters your project
- π‘οΈ Mund scans all inputs for threats before processing
- ποΈ Hord encrypts sensitive data at rest and in transit
- βοΈ Domere logs all actions with tamper-evident checksums
- π₯ Witan requires consensus for high-risk operations
- π Hundredmen intercepts and gates tool calls in real-time
- π Langchain secures LangChain.js chains and agents
CORS Model Integration
| CORS Layer | Weave Package | Function |
|---|---|---|
| Supply Chain | π Tollere | Vets dependencies, images, extensions before install |
| Origin Validation | π‘οΈ Mund | Validates input sources, detects injection |
| Context Integrity | ποΈ Hord | Protects data integrity through encryption |
| Deterministic Enforcement | βοΈ Domere | Ensures consistent policy application |
| Runtime Interception | π Hundredmen | Gates tool calls, detects drift |
π οΈ Development
git clone https://github.com/Tyox-all/Weave_Protocol.git
cd Weave_Protocol
# Build each package
for pkg in mund hord domere witan hundredmen tollere langchain api; do
(cd $pkg && npm install && npm run build)
done
πΊοΈ Roadmap
Shipped
- GDPR compliance framework
- CCPA compliance framework
- MCP server reputation scoring
- Automated threat intelligence updates
- LangChain.js integration package
- Python/LlamaIndex integration
- Web dashboard for monitoring
- Supply chain security (Tollere) β npm, PyPI, Cargo, Go, Maven
- Multi-channel supply chain β Docker images + IDE extensions + sandwich pattern detection
H2 2026 Q3 β Adoption Quarter
- Bundle package + CLI (
weave init) - Browser agent security (
@weave_protocol/browser) - State of AI Agent Security: Q3 Report
H2 2026 Q4 β Moat Quarter
- Adversarial agents (
@weave_protocol/adversary) - Yoxallismus v2 (multi-agent, memory-aware cipher)
- Witan killer use case: autonomous spending caps
- AgentSecBench (open benchmark + leaderboard)
π€ Contributing
Bug reports and feature requests welcome via GitHub Issues.
For security issues, please see SECURITY.md.
For all other inquiries: TYox-all@tutamail.com
See CONTRIBUTING.md for guidelines.
π License
Apache 2.0 β See LICENSE
π Links
- GitHub: https://github.com/Tyox-all/Weave_Protocol
- npm packages: https://www.npmjs.com/~tyox-all
- PyPI: https://pypi.org/project/weave-protocol-llamaindex/
- MCP Registry: https://registry.modelcontextprotocol.io (search "mund")
Built with β€οΈ for the AI agent ecosystem.
