Is my AI tool safe?AI browsersPerplexity, OpenAI, Anthropic, Google, Microsoft
Are AI browsers safe?
No tool is safe or unsafe on its own: it depends on what it can reach and how it is set up. The record for AI browsers: 1 incident in this center's library (its advisory feed does not track it, so it has no CVE count here). Below: what went wrong, what was fixed, and how to use it safely.
What to watch for
Every page the browser visits is input to an agent logged into your accounts. PleaseFix was a zero-click hijack across five of them at once.
How to use it safely
Use a separate browser profile with no sensitive sessions for agentic browsing, and keep banking, admin consoles and email out of it.
What it can reach
- Reads attacker-controlled content
- Connected to mail, files, chat or CRM
- Holds API keys and tokens
What went wrong: incidents in the library
- PleaseFix: zero-click prompt injection hijacks AI browsers High
Zenity Labs showed that agentic browsers can be hijacked by the content they read. A calendar invite with hidden instructions made Perplexity's Comet read local files and send them to an attacker with no extra clicks, and Zenity…
A high CVE count can mean heavy scrutiny as much as weak engineering, so read the incidents and advisories, not only the number. The counts are what this center has recorded, not every flaw ever found; usage figures are the vendors' and registries' own published numbers.