# Defensify Security > Manual Penetration Testing for Web & AI Applications ## Posts - [MCP Tool Poisoning: The Attack Hiding in Your Agent's Tool List](https://blog.defensify.in/mcp-tool-poisoning-attack-guide/): MCP Tool Poisoning: The Attack Hiding in Your Agent’s Tool List The question your team needs to ask next is narrower, and it’s what’s called MCP tool poisoning: what happens when the tool descriptions your agent reads at startup are the attack itself This isn’t a hypothetical we’re raising to sound clever. Since mid-2025, researchers have documented a specific, repeatable attack class against the Model Context Protocol (MCP), the standard most agentic AI products now use to connect models to external tools, files, and APIs. This year it stopped being a research curiosity. A worm campaign used it to plant malicious […] - [Web Application Penetration Testing: Manual Testing vs Automated Scanners](https://blog.defensify.in/web-application-penetration-testing-article/): Ninety percent of the “penetration test reports” we’ve reviewed from other vendors are a vulnerability scanner’s PDF export with a logo on it. Missing security headers, an outdated library version, a couple of low-severity findings, and a bill. No authentication flows tested. No business logic touched. No proof that a human ever looked at the application. That gap is the entire reason web application penetration testing exists as a discipline separate from vulnerability scanning. This guide covers what a real web app pentest actually involves, how manual testing differs from automated scanning, what OWASP’s current risk list covers, and what a […] - [OWASP Top 10 for LLM Applications: The 2025 List Explained](https://blog.defensify.in/owasp-llm-top-10-2025-full-list-explained/): Sensitive Information Disclosure went from the #6 risk in the original OWASP LLM list to #2 in the 2025 update. That’s not a cosmetic reshuffle – it reflects a wave of real incidents where LLM applications leaked training data, credentials, or internal configuration through nothing more exotic than a well-crafted query. If your team is building or shipping anything backed by an LLM – a chatbot, a RAG pipeline, an agent that calls tools – the OWASP Top 10 for LLM Applications is the closest thing the industry has to a shared risk checklist. This guide walks through the current 2025 […] - [What is Prompt Injection? A Complete Guide for Engineering Teams](https://blog.defensify.in/what-is-prompt-injection/): If your product uses an AI assistant, a chatbot, or an LLM-powered feature, prompt injection is the most important attack class your team needs to understand right now. It does not require sophisticated malware. It does not need privileged access. In many cases, it takes one carefully worded sentence. This guide explains what prompt injection is, how it works in practice, and what engineering teams should do about it. What is Prompt Injection? Prompt injection is an attack where a malicious user manipulates the input to an AI system to override its original instructions and make it behave in unintended ways. […] ## Pages - [Home](https://blog.defensify.in/home/) ## Optional - [Agent (MCP protocol)](websites-agents.hostinger.com/blog.defensify.in/mcp) [comment]: # (Generated by Hostinger Tools Plugin)