Prompt Injection Vulnerability occurs when an attacker manipulates a large language model (LLM) through crafted inputs, causing the LLM...
LLM02: Insecure Output Handling
Insecure Output Handling refers specifically to insufficient validation, sanitization, and handling of the outputs generated by large language models...
LLM03: Training Data Poisoning
The starting point of any machine learning approach is training data, simply “raw text”. To be highly capable (e.g.,...
LLM04: Model Denial of Service
An attacker interacts with an LLM in a method that consumes an exceptionally high amount of resources, which results...
LLM05: Supply Chain Vulnerabilities
The supply chain in LLMs can be vulnerable, impacting the integrity of training data, ML models, and deployment platforms....
LLM06: Sensitive Information Disclosure
LLM applications have the potential to reveal sensitive information, proprietary algorithms, or other confidential details through their output. This...
LLM07: Insecure Plugin Design
LLM plugins are extensions that, when enabled, are called automatically by the model during user interactions. They are driven...
LLM08: Excessive Agency
An LLM-based system is often granted a degree of agency by its developer – the ability to interface with...
Overreliance can occur when an LLM produces erroneous information and provides it in an authoritative manner. While LLMs can...
This entry refers to the unauthorized access and exfiltration of LLM models by malicious actors or APTs. This arises...
The full story
This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.
