Open Worldwide Application Security Project

OWASP has updated its list of the top 10 most critical vulnerabilities of LLM applications, with prompt injection and sensitive information disclosure remaining the two most severe threats and excessi…

Adversarial prompting, the practice of crafting inputs to make large language models deviate from their intended behavior, has become the top exploit category in the OWASP Top 10 for LLM Applications …

A malicious PyPI package named 'ColorLib' was discovered targeting developers with info-stealing malware that exfiltrates environment variables, cryptocurrency wallet details, and credentials. OWASP r…