AI agents are becoming the new attack surface, exposed to poisoned skills, prompt injection, jailbreaks and attacks through connected tools. I read the AI security research published in a single month, February 2026, and when you put it all together, it’s not a list of curiosities. It’s a field guide to a new attack surface.
The Target Is No Longer the Model. It’s the Agent.
About this summary. This is a short, independently written summary of an article first published by Security Affairs. Cyber Security News did not report or verify the underlying story. Read the original: https://securityaffairs.com/199454/ai/the-target-is-no-longer-the-model-its-the-agent.html
Source attribution: headline and facts are from Security Affairs (securityaffairs.com). Summary method: excerpt of the source description. See our source attribution policy.
Related coverage
Defusing Explosive Prompts: Understanding and Preventing Trigger-Based Prompt Injections in LLM Agents
arXiv:2609.22510v1 Announce Type: new Abstract: As LLM applications integrate with external tools, they are increasingly exposed to indirect prompt injection (IPI)…
Beyond Single-Model Injection: A Threat Model and Defense Architecture for Prompt Injection in Multi-Agent Systems
arXiv:2609.22949v1 Announce Type: new Abstract: Existing prompt injection research focuses on single-model chatbot scenarios, where an attacker manipulates one LLM…
Origin Is All You Need: Provenance-Aware Transformers for Structural Trust-Boundary Separation
arXiv:2609.21088v1 Announce Type: new Abstract: Indirect prompt injection (IPI) remains a central safety and security challenge for large language model (LLM) systems…
SECURITY AFFAIRS MALWARE NEWSLETTER ROUND 115
Security Affairs Malware newsletter includes a collection of the best articles and research on malware in the international landscape Malware Newsletter Gray Rabbits and…
Shai-Hulud Attack Nips Cyber-Firm CrowdSec's GitHub Data
Threat actors stole 170 private repositories using an OAuth token stolen from a former employee's computer through the TanStack npm supply chain attack.
Critical Bifrost AI Gateway Flaw Lets Attackers Run Commands Without Credentials
A critical vulnerability in Bifrost, an open-source AI gateway that routes requests to more than 20 LLM providers, allows an unauthenticated attacker to run arbitrary…