Skip to content
EVENT / TOPICHistorical

Parameter Labs Reports ChatGPT Artifacts Mode Security Vulnerability

1 reports1 sources10/31/2026 updated

Current overview (not historical)

AI overview

Parameter Labs discovered a complex attack chain in ChatGPT's artifacts mode, exploiting the YouTube oEmbed endpoint to execute reflective JavaScript and steal user private data. OpenAI has closed the vulnerability and paid a $5,000 bounty.

Written with AI from the reporting · updated 11/1/2026

Expand the detailed fact route and sources

Story route

A station-by-station route from the first public evidence onward; every station carries its own evidence and uncertainty.

  1. 1Unclassified fact stationOct 31, 00:00recorded Nov 1, 08:23single sourcerevised

    Parameter Labs发现ChatGPT artifacts模式安全漏洞

    Read original source ↗ Simon WillisonReplay this moment in the explorer
    Evidence & revisions · 1 source records
    Subject:
    openai
    Action:
    闭合安全漏洞并支付$5000奖金
    Object:
    ChatGPT accounts
    Occurred (fact side):
    Oct 31, 00:00
    Simon Willison ↗Report pageRevision 2 · currently revised
    Published (valid side):
    Nov 1, 07:15
    First seen (known side):
    Nov 1, 08:23
    Fact stationSingle source · one-sided claimRevised

    Copy may have been revised later; time replay is bounded. Layer labels group reading only, not causation between layers.

Uncertainty marks flag where to check the sources; they are not proven causation.

Report timeline

Explore every side through dated source reports.

Nov 1
  1. Simon WillisonSelectedRelated fact: single sourceSource report revised
    Parameter Labs discovers exploit in ChatGPT's artifacts feature allowing data exfiltration

    Report first recorded Nov 1, 08:23

    Parameter Labs found a complex attack chain in ChatGPT's artifacts feature that allows untrusted code in a sandboxed iframe to execute JavaScript and exfiltrate private user data. The exploit leverages the MathLive library's virtual keyboard triggered via postMessage(), and uses the YouTube oEmbed endpoint to bypass OpenAI's Content Security Policy and execute scripts. Once JavaScript runs, the attacker can access private APIs and steal data via image references, enabling data theft or unauthorized actions when a victim visits a specially crafted share URL.

    Read original source ↗

Event activity trend

Latest comparable
3
Comparable peak
10Nov 1, 09:00
24h change
-50%

The chart compares consistently observed participants only. Hover or tap to inspect each hour; use arrow keys to move between observations.

Event discussion

Reader opinions are hosted on GitHub Discussions; posting requires a GitHub account. Comments are not verified facts.

Open GitHub Discussions