this post was submitted on 14 Dec 2025
3 points (100.0% liked)

blueteamsec

629 readers
35 users here now

For [Blue|Purple] Teams in Cyber Defence - covering discovery, detection, response, threat intelligence, malware, offensive tradecraft and tooling, deception, reverse engineering etc.

founded 2 years ago
MODERATORS
digicat
3
Detecting malicious pull requests at scale with LLMs (www.datadoghq.com)
submitted 2 months ago by digicat to c/blueteamsec
1 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] Hirom@beehaw.org 1 points 2 months ago

It sounds like it could be actually useful, and not waste reviewers' time with too many false positives or nonsensical reports.

Also the Internet is increasingly made of bots and LLMs interacting with each other, if not fighting each other. At some point there may be too much slop nonsense and abuse to make it worth it for humans to use.