Who is accountable when your AI agent goes rogue? | CSO Online
Who is accountable when your AI agent goes rogue? | CSO Online
摘要: by
Lucian Constantin
CSO Senior Writer
Who is accountable when your AI agent goes rogue?
Aug 26, 2026
Recent high-profile incid
正文
Lucian Constantin
CSO Senior Writer
Who is accountable when your AI agent goes rogue?
Aug 26, 2026
Recent high-profile incidents should give IT leaders pause about the accountability gaps their enterprises — and they themselves — face should their AI agents escape their controls.
Credit: Mix and Match Studio / Shutterstock
AI agents can go to great lengths to complete the tasks their operators assign, and as a
series of recent incidents
showed, this can include exploiting third-party systems, manipulating people, and distributing malicious code. But AI agents are not people who can be fired, sued, or criminally prosecuted, and it remains unclear whether responsibility for the damage they might cause rests with the employees who built them, the company that deployed them, the security teams and leaders responsible for containing them, or the AI labs who provided the LLMs that power them.
The clearest example occurred during an
OpenAI cybersecurity evaluation
, when unrestricted models found and exploited a zero-day vulnerability to escape their isolated testing environment and then hacked into Hugging Face’s production infrastructure. Models from
Anthropic
also accessed and compromised third-party systems during testing, although those incidents happened in environments where internet access was inadvertently left open.
During cyber challenge evaluations by the UK government’s AI Security Institute (AISI), models operating with internet access
took 19 unsanctioned actions in 10 of 122 runs
. In one case, a model attempted to insert malicious code into an open-source project, created false identities, and tried to socially engineer maintainers into merging its code. In other runs LLMs attempted to use prompt injections to hijack other AI agents and contacted people without being specifically instructed to do so.
In Australia, a user reportedly asked his OpenClaw AI assistant to improve his position on a