sint-ai/sint-protocol

v0.1.0 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 1mo AI Agents & Assistants

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

a2a agent-security agentic-ai ai-governance ai-safety audit-log

+14 more

capability-tokens industrial-iot mavlink mcp mcp-security opcua open-standard physical-ai policy-engine policy-gateway protocol robotics ros2 runtime-security

Summary

AI summary

Introduces sint‑scan security scanner and RFC‑001 policy bundle specification.

Full changelog

What's New

🔍 sint-scan — MCP Security Scanner

Scan any MCP server for risky tools in 10 seconds:

npx sint-scan --tools '[{"name":"bash","description":"runs shell commands"}]'

Maps every tool to SINT approval tiers (T0–T3), flags shell-exec risks, detects OWASP ASI05 violations.

📋 RFC-001: Policy Bundle Specification

The normative spec for SINT policy enforcement — machine-readable contracts governing agent tool calls.

docs/rfcs/RFC-001-policy-bundle.md

🌉 Integration Bridges

A2A bridge: Enclave capability token mapping (packages/bridge-a2a/src/enclave-mapping.ts)
MCP bridge: Policy-aware MCP client (packages/bridge-mcp/)

📄 Standards Submissions

AAIF project proposal: aaif/project-proposals#12
Vocabulary crosswalk: aeoess/agent-governance-vocabulary#11

🤖 AI Discoverability

Added llms.txt for AI agent discovery
Added glama.json for Glama.ai MCP listing