ChatGPT’s new feature could give infostealers a map of your Mac activity
OpenAI's Computer History feature for macOS ChatGPT logs app and website activity into memories, raising prompt injection and infostealer privacy risks.
OpenAI's Computer History builds timelines of Mac activity from interaction events and macOS accessibility data, turning them into memories for ChatGPT and Codex. The feature is opt-in, requires Memories, runs only in the ChatGPT macOS desktop app, and is unavailable in the EEA, Switzerland, and the UK. Raw event files stay on-device and are deleted after 48 hours, but generated Markdown memory files are unencrypted and persist until manually deleted. OpenAI itself flagged unencrypted files and prompt injection risks, and security experts warned infostealers could use the logs as a ready-made map of someone's workday.
- Feature is opt-in, off by default, and requires OpenAI's Memories to be enabled.
- Raw interaction events stay on-device and are deleted after 48 hours.
- Unencrypted Markdown memory files could be read by other programs under the same macOS user.
- OpenAI warns malicious web content could trigger prompt injection through ChatGPT or Codex.
- Unavailable in the EEA, Switzerland, and the UK; macOS desktop app only.
- Organizations
- OpenAIMalwarebytesAppfireHelp Net Security
From the original article
2 min read at helpnetsecurity.com
OpenAI’s new Computer History feature turns recent Mac computer activity into memories ChatGPT and Codex can use, and it’s raising questions about privacy and security along the way. Computer History builds a timeline out of everyday computer use, grouping activity into summaries and noting which apps and websites contributed to each one.
By @helpnetsecurity · helpnetsecurity.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.