I am not a super code-literate person so bare with me on this… But. Still please becareful. There appears to be a vulnerability.
Users are posting images like the following:
And inside hidden is JavaScript code that when executed can take cookie information and send it to a URL address.
Among other things. At this time if you see an image please click the icon circled before clicking the link. DO NOT CLICK THE IMAGE. If you see anything suspicious, please report it immediately. It is better a false report than a missed one.
If anything this is probably a vulnerability in a browser implementation (or one of the apps). I’d be surprised if Lemmy in and of itself is vulnerable to an attack via embedded JS in a picture.
I am too dumb to explain it, so here is chatgpt doing it for me:
Explain code’s functionality.
ChatGPT The code you provided is a URL that includes an onload event attribute. This attribute is commonly used in HTML to specify a JavaScript code that should be executed when an element, such as an image, finishes loading.
In this specific case, the onload event is set to the following JavaScript code:
javascript [Redacted] This code performs the following actions:
It constructs a URL by concatenating a base URL ([redactedurl].zip/save/) and a string representation of a cookie value. The cookie value is obtained by concatenating the document.cookie property, which contains the cookies associated with the current page, and the id property of an element retrieved using document.getElementById(). The id property is obtained by retrieving an element with the ID represented by the string of character codes (String.fromCharCode(110,97,118,65,100,109,105,110)), which translates to the string “navAdmin”. If no element with the ID “navAdmin” is found, an empty object {id:String.fromCharCode()} is used instead. The resulting URL is then passed as an argument to the fetch() function, which initiates a network request to that URL. In summary, this code appears to be attempting to send a network request to a dynamically constructed URL that includes the value of the document.cookie property and the id property of an element with the ID “navAdmin” if it exists. The purpose and intention of this code cannot be determined without further context. However, it’s worth noting that such code could potentially be used for malicious purposes, such as stealing sensitive information from users.
No offense, but I think you’re putting too much trust on the Lemmy code. I’m not saying the code is bad, but it’s just as likely as other codes that the vulnerability is in Lemmy’s code.
But lemmy itself shouldn’t really interact with the images in terms of decoding them. Just having the code in the image may be weird but it should only affect code that actually tries to read and understand the bytes. Just passing it around shouldn’t cause the code to be executed.
And the real decoding and displaying is hopefully done by the browsers Codebase, not by anything Lemmy does itself.
At least that’s my line of reasoning. I may very well be off here.
Doesn’t affect my mobile client
deleted by creator
