Blog Post
| A threat intel feel for agentic AI: Get AgentMesh Today |
Executive Summary
The AI agent ecosystem is growing fast and so is its attack surface. MCP servers, VS Code extensions, AI skills, and coding agent tools are being weaponized at a pace that traditional threat intelligence hasn't kept up with.
Today, we're excited to announce that Knostic's AgentMesh is joining VirusTotal's Crowdsourced AI program, bringing agentic supply chain threat intelligence directly into one of the world's most widely used security platforms.
What AgentMesh Brings to VirusTotal
AgentMesh continuously discovers, tracks, and scans AI agent skills, MCP servers, and IDE extensions for prompt injection and supply chain threats. As part of VirusTotal's Crowdsourced AI lineup, AgentMesh adds a new analysis stream purpose-built for the agentic layer, where the tools and plugins that AI coding assistants and autonomous agents rely on to operate.
For every MCP server and VS Code extension submitted to VirusTotal, AgentMesh will surface:
- A clear verdict (benign, suspicious, or malicious) based on behavioral analysis
- Detection of prompt injection payloads embedded in tool descriptions or responses
- Supply chain risk signals, including typosquatting, unexpected network behavior, and secret exfiltration patterns
- Searchable results in VirusTotal Intelligence
Why this matters now
Knostic Labs has been tracking the rapid militarization of the AI agent supply chain. In 2026 alone, we've documented campaigns like Glassworm, SaassyCode, and a supply chain breach via the Nx Console VS Code extension, all targeting developers via the very tools their AI agents consume. These threats are fast-moving, hard to detect with traditional AV signatures, and increasingly consequential as agents gain real execution capabilities.
VirusTotal's crowdsourced model, which aggregates independent AI engines across file types and threat classes, is exactly the right architecture for this problem.
Explore AgentMesh Threat Intelligence
You can start using AgentMesh today at agentmesh.knostic.ai, where we publish our running feed of discovered and analyzed AI agent components. VirusTotal users will be able to query AgentMesh verdicts directly in VT Intelligence as the integration rolls out.
The threat to the AI agent supply chain is real, growing, and undermonitored. We're proud to work alongside VirusTotal and the broader AI Security community to change that.
Subscribe to our blog!
Data Leakage Detection and Response for Enterprise AI Search
Learn how to assess and remediate LLM data exposure via Copilot, Glean and other AI Chatbots with Knostic.
The Data Governance Gap in Enterprise AI
See why traditional controls fall short for LLMs, and learn how to build policies that keep AI compliant and secure.
Rethinking Cyber Defense for the Age of AI
Learn how Sounil Yu’s Cyber Defense Matrix helps teams map new AI risks, controls, and readiness strategies for modern enterprises.
Extend Microsoft Purview for AI Readiness
See how Knostic strengthens Purview by detecting overshared data, enforcing need-to-know access, and locking down AI-driven exposure.
Build Trust and Security into Enterprise AI
Explore how Knostic aligns with Gartner’s AI TRiSM framework to manage trust, risk, and security across AI deployments.
Real Prompts. Real Risks. Real Lessons.
A creative look at real-world prompt interactions that reveal how sensitive data can slip through AI conversations.
Stop AI Data Leaks Before They Spread
Learn how Knostic detects and remediates oversharing across copilots and search tools, protecting sensitive data in real time.
Accelerate Copilot Rollouts with Confidence
Equip your clients to adopt Copilot faster with Knostic's AI security layer, boosting trust, compliance, and ROI.
Reveal Oversharing Before It Becomes a Breach
See how Knostic detects sensitive data exposure across copilots and search, before compliance and privacy risks emerge.
Unlock AI Productivity Without Losing Control
Learn how Knostic helps teams harness AI assistants while keeping sensitive and regulated data protected.
Balancing Innovation and Risk in AI Adoption
A research-driven overview of LLM use cases and the security, privacy, and governance gaps enterprises must address.
Secure Your AI Coding Environment
Discover how Kirin prevents unsafe extensions, misconfigured IDE servers, and risky agent behavior from disrupting your business.
