A Flaw in ChatGPT’s Mac App Could Have Let Hackers Grab Sensitive Data
Researchers at the Objective-See Foundation discovered a critical vulnerability in the macOS version of ChatGPT that could allow attackers to access sensitive user data. The flaw exploited a trusted script interpreter to bypass security checks, granting unauthorized access to chat logs and system commands. OpenAI has patched the issue, highlighting the growing security risks associated with the extensive system permissions required by AI applications.
- ▪The vulnerability allowed attackers to take over the ChatGPT app on a victim's computer to access chat logs and browser sessions.
- ▪Researchers found that a trusted script interpreter could be manipulated to deliver untrusted scripts into the main ChatGPT process.
- ▪The exploit was described as trivial to execute, requiring only about a dozen lines of code to demonstrate.
- ▪OpenAI acknowledged the flaw and applied a fix, noting a need to accelerate their security practices.
- ▪The discovery underscores the security risks posed by the deep system access and trust that AI platforms require to function.
WIRED files mainly under tech. We currently carry 1,008 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | WIRED |
| Canonical URL | https://www.wired.com/story/a-flaw-in-chatgpts-mac-app-could-have-let-hackers-grab-sensitive-data/ |
| Publication time | Fri, 02 Oct 2026 09:45:00 +0000 |
| Retrieval time | 2026-10-02T09:50:44.485Z |
| Last seen | 2026-10-02T09:50:44.485Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | NpUUFVHtlngr · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Lily Hay NewmanMatt BurgessSecurityOct 2, 2026 5:45 AMA Flaw in ChatGPT’s Mac App Could Have Let Hackers Grab Sensitive DataWhile the focus has been on AI agents’ hacking capabilities, a recently patched vulnerability in a ChatGPT app shows that AI software is itself an inviting—and vulnerable—target.Photograph: Brendan Smialowski/Getty ImagesCommentLoaderSave StorySave this storyCommentLoaderSave StorySave this storyHardly a day goes by lately without news of AI agents autonomously hacking websites or AI tools being used by cybercriminals and scammers.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at WIRED.
Discussion
0 commentsMore from WIRED
