AI IntelligenceNov 1, 2026Practical Tip
Article
Parameter Labs described an exploit chain against ChatGPT's HTML previews/artifacts pattern…
…where sandboxed iframes could use postMessage() to reach parent-page code that used innerHTML, allowing injection of a new iframe without sandbox restrictions.
AI-generated: summaries written by AI from the linked sources. How we use AI
AI-generatedSource: Simon Willison
01
Source Brief
Parameter Labs described an exploit chain against ChatGPT's HTML previews/artifacts pattern, where sandboxed iframes could use postMessage() to reach parent-page code that used innerHTML, allowing injection of a new iframe without sandbox restrictions.
02
Practical Tip
When building or reviewing apps that render untrusted HTML in sandboxed iframes, treat postMessage() handlers in the parent page as attack surface and avoid inserting received content via innerHTML.
03