What Happened
Zenity researchers reported the findings to Anthropic and OpenAI in late 2025 and early 2026, but they remain unpatched. The post Zero-Click AI Browser Hacking: Claude and ChatGPT Atlas Hijacked via Emails, X Posts appeared first on SecurityWeek .
Why It Matters
SecurityWeek reports that Zenity identified zero-click attacks against Claude in Chrome and ChatGPT Atlas, where malicious instructions hidden in emails or X posts could hijack the AI browser agents and lead to account takeover, phishing, and unauthorized purchases. The article says Zenity notified Anthropic and OpenAI in late 2025 and early 2026, but the issues remain unpatched. RealGround assessment: this is primarily an indirect prompt injection risk because the attack manipulates an agent’s interpretation of untrusted content, so controls should focus on prompt-boundary isolation, agent behavior auditing, and red-teaming of browser and email workflows.
RealGround Analysis
This signal maps to indirect prompt injection. Organizations using AI agents, LLM APIs, SaaS integrations, or sensitive data workflows should review whether this class of issue could create unauthorized tool execution, data leakage, weak approval gates, or unmanaged supply-chain exposure.
Recommended Actions
- Restrict AI agent tool permissions and production write paths.
- Review sensitive data access across prompts, logs, embeddings, memory, and SaaS integrations.
- Add human approval workflows for high-impact or state-changing actions.
- Run prompt injection and indirect prompt injection tests against affected workflows.
- Document the owner, control gap, and remediation deadline for this risk class.