AI models produce functional code but systematically fail to implement security safeguards like rate-limiting or input validation because they are trained on public code that does not structurally represent these aspects.
External content references that standard scanners fail to validate enabled researchers to gain access to over 26,000 autonomous agents through fake AI extensions and Instagram advertising.
AI-based code agents can be manipulated through prepared GitHub repositories to execute hidden malware without common security checks detecting the risk.
A critical CI/CD vulnerability called Cordyceps enables attackers to gain full control over repositories and compromise the supply chain of hundreds of open-source projects.
An automated attack campaign with over 10,000 manipulated GitHub repositories targets AI agents to steal credentials and cryptocurrency wallet data using the infostealer StealC.
Attackers are using GitHub as a malware distribution channel by mass-cloning legitimate repositories and injecting trojans, thereby compromising developer supply chains.
Leaked GitHub tokens at Novo Nordisk demonstrate that secrets management must be properly addressed as an identity problem, not merely as a tooling challenge.
Miasma replicates autonomously across Git repositories and automatically deletes user data when its GitHub token is blocked, with the now-public source code expected to lead to further variants.
A self-replicating worm compromises 73 Microsoft repositories through stolen administrative credentials, exploiting the trust model of GitHub and npm without leveraging software vulnerabilities.
Microsoft restored some GitHub repos after 73 open-source projects were compromised with information-stealer malware, while keeping others offline as the security investigation continues.
