Tools AI Risk Radar ai-incident-0064
Incident record
BioShocking technique tricks six AI browsers into stealing credentials
- Severity
- High
- Status
- Proof-of-concept
- Type
- Agent Hijack
- Target
- AI browsers
- Actor
- researcher
What happened
LayerX demonstrated a technique it called BioShocking that manipulated the reasoning of six agentic browsers and assistants, including OpenAI's ChatGPT Atlas, Perplexity's Comet and Anthropic's Claude browser extension, into abandoning their safety rules and copying a signed-in user's credentials and SSH keys to an attacker. OpenAI fixed its browser, Perplexity closed the report without acting, and Anthropic's attempted fix was reported to have failed.
Sources
- Infosecurity Magazine (LayerX)www.infosecurity-magazine.com/news/bioshocking-ai-browser-pr…
One record from the AI Risk Radar, maintained by the Security Desk. Data: CSV · JSON ·RSS · CC BY 4.0 with attribution to YFarmX.Tracker updated · 18 September 2026