Comment by toyg
1 day ago
> You could download the extension, diff it against the previous version and read all the code.
This would actually be an exceptionally good use-case for AI. You don't need a super-duper frontier model to download a bit of source-available code and check for suspicious signs, any cheap model would do well enough. Heck, it's effectively virus scanning, we've had that for decades.
Cursor explicitly claims "Before an extension is shown in search or served as a download, Cursor runs automated malware and supply-chain analysis using commercial security tooling. Extensions that fail review are blocked. Cursor also monitors extension-ecosystem threat intelligence and updates its blocklist over time."
However, the bad extension was live for ~11 hours.
That's a testament to the strength of their so called "commercial quality" security tooling.
Norton Anti Virus...
LLM are not designed for that. Unless prompt injection is really solved I would avoid showing LLM untrusted code.
The CTA flavor of the year for dev tools is cURLing some arbitrary install script and run it immediately which always sounded ridiculous to me. If instead that script first pipes into claude -p for a basic vulnerability scan before continuing, I would be delighted.
Hopefully a well-sandboxed claude -p.