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

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 Missing security headers, an outdated library version, a couple of low-severity findings, and a bill.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

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

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