Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

Threat actors continue to rely on social engineering as AI is incorporated into their attacks, according to ESET’s Threat Report for the first half of 2026. ESET’s Director of Threat Prevention Labs, Jiří Kropáč, stated, “Rather than relying on entirely new methods and tools, attackers are quickly adapting established techniques to new platforms, technologies, and user behaviors.

Coding agent security has a framing problem. Most security conversations around these tools center on the wrong question. 'Did the agent have permission to do that?' is a reasonable place to start, but in the context of autonomous AI systems, it's not where the risk actually lives. In Zenity Labs' research into the coding agent threat model, the pattern that keeps surfacing isn't that agents are doing things they aren't allowed to do.

An AI agent on a developer's laptop has read access to a code repository, a set of internal documents, and an external model. Nobody approved that specific combination, and nobody is watching what the agent does with it session to session. The agent is not malicious, however, it is doing exactly what it was configured to do. But, that configuration is the exposure, and most security teams do not have a way to see it, let alone stop it before sensitive data leaves the environment.