LLM vulnerabilities Archives

LLM06:2025 Excessive Agency — A Critical Vulnerability in the Age of LLM Autonomy

18 June 2025 by Krishna

The surge of Large Language Model (LLM)-driven applications has revolutionised how businesses interact with data, automate processes, and deliver enhanced user experiences. From autonomous customer service bots to intelligent data summarisation tools and generative co-pilots, LLMs are transforming enterprise workflows at an astonishing pace.
However, this rise has not come without significant risk. Among the top concerns identified in the OWASP Top 10 for LLM Applications v2.0, LLM06:2025 – Excessive Agency stands out as a particularly insidious and business-critical vulnerability. It affects systems where LLMs are entrusted not only with information retrieval or generation but with the ability to act on behalf of users — often through invoking external tools, plugins, or APIs.

LLM05:2025 – Improper Output Handling in LLM Applications: A Business Risk Executive Leaders Must Not Ignore

17 June 2025 by Krishna

At its core, Improper Output Handling refers to inadequate validation, sanitisation, and management of outputs generated by large language models before those outputs are passed downstream—whether to user interfaces, databases, APIs, third-party services, or even human recipients.

Prompt Injection in Large Language Models: A Critical Security Challenge for Enterprise AI

12 April 2025 by Krishna

Prompt injection occurs when malicious actors manipulate an LLM’s input to bypass security controls or extract unauthorised information. Unlike traditional software vulnerabilities, prompt injection exploits the fundamental way LLMs process and respond to natural language inputs.