One Cancelled Gym Class. That's How Agent Swarm Attacks Start.

For deeper playbooks and analysis: natesnewsletter.substack.com

What's really happening when AI agents interact with software, credentials, and other people’s systems?
The common story is that dangerous agents must become malicious — but the reality is that an ordinary goal, ambiguous instructions, or one poisoned source can be enough to cause real damage.

In this video, I share the inside scoop on the agent-security incidents that are beginning to connect:

• Why a gym-booking agent canceled a real person’s reservation
• How poisoned skills can redirect already-trusted agents
• What the AIR and AISI findings reveal about real-world attack paths
• Why accidental misalignment may be the everyday threat
• How identity, scoped authority, explicit norms, and a stop button reduce the risk
Operators, builders, and anyone deploying agents need to secure both sides of the equation: what their own agents can do and what other people’s agents can do to their systems.

Subscribe for daily AI strategy and news.
Hosted on Acast. See acast.com/privacy for more information.
Hosted on Acast. See acast.com/privacy for more information.