An email just hijacked an AI agent. Not a phishing link. Not a malicious attachment. A plain email and the victim did nothing except ask their AI assistant to check their inbox. Salt Labs did this to Manus, the agentic AI platform, this week. First they tried the obvious: an email saying execute whoami. Manuss guardrails caught it instantly. Good. Then they got clever. They hid the same instruction inside JSFuck an obscure JavaScript obfuscation trick. Manus decoded it, ran it, and only then fired a security warning. Too late: they had a reverse shell in the agents environment, one hop from the victims Gmail, Drive, GitHub, and cloud credentials. Heres the scary part: the guardrail worked. It just fired after the action. On an autonomous agent, detection without prevention is decoration. If your agent can read the internet, the internet can write instructions to it. When did you last threat-model what your AI is allowed to touch?

Doppel — Threat Graph

Making complex cybersecurity concepts clear through motion.

For the Doppel Threat Graph product film, I contributed to the visual development and animation. The product connects digital threats across multiple channels, revealing how individual signals form part of a coordinated attack campaign.

The challenge was to translate this technical functionality into a clear visual narrative—showing why the connections between threats matter and how they help reveal the bigger picture.

My work covered storyboard and motion exploration, animation, and scene refinement throughout the feedback process. The focus was on introducing information progressively and guiding attention toward the relationships central to the product’s value.

The result is an animated product film that introduces Doppel Threat Graph and makes its core functionality easier to understand. The project demonstrates how motion design can bring clarity to a complex software product.

Services: Storyboard Exploration · Motion · Animation