Skip to main content
USA-Based Digital Agency

AI security · Updated

AI security for apps, agents, MCP servers and AI-written code

AI changes security in two ways. Apps and agents built on language models can be steered by text an attacker writes, and code written with AI assistants arrives faster than teams can review it. This hub collects our guides on both, each built on primary sources, and the reviews and audits we run to find and fix the problems.

By George Shvaya, founder of Webvello · Published

Key takeaways

  • Prompt injection is first on the OWASP Top 10 for LLM Applications, and OWASP, the UK NCSC and the model vendors all say it cannot yet be fully prevented.
  • The MCP specification documents risks including confused deputy, token passthrough and SSRF, and two MCP developer tools had critical CVEs in 2025.
  • Veracode’s 2025 tests found AI-generated code introduced security vulnerabilities in 45% of cases.
  • CISA’s KEV catalog listed 1,781 vulnerabilities exploited in the wild as of November 16, 2026, the first signal for which dependency alerts to fix.
  • The defenses are mostly ordinary security engineering applied consistently: least privilege, review, validation and patching.

Which AI security risks matter most right now?

Where each risk shows up and where to read more.
Common AI security risks, where they appear and the related guide
RiskWhere it shows upGuide
Prompt injectionChatbots, RAG features, agents reading email, web pages or filesPrompt injection
Excessive agencyAgents with broad tools, credentials or no approval stepsOWASP LLM Top 10
Tool poisoning and token passthroughMCP servers and the assistants that connect to themMCP security risks
Insecure generated codeCode written with Copilot, Claude Code, Cursor or CodexAI coding assistant security
Hallucinated and malicious packagesDependencies suggested by AI or updated automaticallyDependency triage

How we approach AI security

Defensive, evidence-first and specific to how your app actually uses AI.
  • We start from what the model can reach, because that sets the worst case for every other risk.
  • We follow public standards: the OWASP Top 10 for LLM Applications, the MCP specification, and CISA and FIRST guidance for vulnerabilities.
  • Findings come with evidence and a fix, ranked by real risk rather than scanner severity alone.
  • We test only systems you own or are authorized to test, and we prefer staging environments.

Webvello’s founder, George Shvaya, studied cybersecurity and information assurance and comes from networking and information security. We also build the systems we review: MCP servers, AI agents and Claude Code rollouts. Rules that affect AI tools, such as the FCC’s ruling on AI voices, are in our rules tracker; the OWASP GenAI Security Project is the best place to follow the field.

Pages that go deeper on the pieces this one touches.

Common questions

Straight answers to what owners ask us first.

What is AI security?

AI security covers the risks that come from building with AI models: attackers steering a model with injected text, agents with too much access, data leaking through prompts or retrieval, and insecure code or packages introduced by AI coding tools. It sits alongside ordinary application security rather than replacing it.

Do small companies need an AI security review?

If an AI feature can read customer data, send messages, change records or run code, yes. A review scoped to one feature is small, and it is cheaper than finding out from a customer.

What happens after I ask for a free security review?

You describe your app, agent, MCP server or codebase. A person replies with what we would check first and what a full review or audit would involve.

Find the gaps before someone else does

Book a call or describe your app, agent, MCP server or codebase, and we will scope a review.