Threat Library

Agent-to-agent threats first — conventional coverage one click away.

Browse by hub: AI agent threats · Conventional watchlist · OWASP Agentic Top 10

TypeAll Prompt Injection Tool Poisoning Memory Poisoning Agent Worm Framework Vulnerability Protocol Vulnerability

Showing 1 of 21 threats

Kong Konnect MCP Server Indirect Prompt Injection VulnerabilityhighAgent

MCPindirect-prompt-injectionkong-konnectapi-gatewaytool-misuseCVE-2026-13341ASI01 · Goal HijackingAML.T0051AML.T0054Surface: ProtocolPropagation: Single Hop

Kong Konnect's Model Context Protocol server prior to version 1.0.0 is vulnerable to indirect prompt injection, allowing a remote attacker to manipulate an LLM agent into executing unintended API requests. This effectively lets an attacker who controls untrusted content processed by the MCP server hijack the agent's actions against Kong-managed APIs, with a CVSS score of 7.4 indicating high severity.

▾