spiffy-oss/artguard
Open-source AI artifact scanner. Detect malicious agent skills, MCP servers, and IDE rule files before they run.
It employs a multi-layered approach, combining privacy posture analysis, LLM-powered semantic instruction analysis, and static pattern matching to detect complex threats within natural language instructions and configuration files. The scanner outputs a structured Trust Profile JSON, designed to integrate with policy engines and audit trails. It requires Python 3.11+, leverages the Anthropic API for deep semantic analysis, and integrates YARA rules and other open-source tools for traditional static analysis.
Stars
24
Forks
—
Language
—
License
MIT
Category
Last pushed
Mar 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/spiffy-oss/artguard"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AgentSeal/agentseal
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor...
Nebulock-Inc/agentic-threat-hunting-framework
ATHF is a framework for agentic threat hunting - building systems that can remember, learn, and...
HeadyZhang/agent-audit
Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis....
affaan-m/agentshield
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool...
LucidAkshay/kavach
Tactical AI Workspace Monitor & EDR