Weekly Update – 25 Sep 2025 When I talk to peers across the security community, one theme keeps coming up: artificial intelligence has changed the threat landscape in ways that are both profound and unsettling. Attackers have always been creative, but now they're creative at scale. With the help of AI, they can move faster, automate more effectively, and discover weaknesses that would have taken a human weeks or months to uncover. The post AppSec in the age of AI-powered attacks: Are your apps ready? appeared first on Invicti.
It is common for companies to have some kind of large language model (LLM) application exposed in their public-facing systems, often as a chatbot. LLMs usually have access to additional tools and MCP servers to call external systems or perform specialized operations. These tools are an underestimated yet critical part of the attack surface and can be exploited by attackers to compromise the application via the LLM. The post When your AI chatbot does more than chat: The security of tool usage by LLMs appeared first on Invicti.
The OWASP Top 10 for LLM Applications (2025) highlights the leading technical and socio-technical risks facing enterprises as they scale generative AI. See what's changed since the previous edition and learn how Invicti's proof-based scanning and LLM-specific security checks can help organizations validate real risks and strengthen defenses across AI-driven applications. The post OWASP Top 10 risks for LLMs (2025 update) appeared first on Invicti.
More Recent Articles
|
No comments:
Post a Comment