A critical vulnerability in OpenAI Group PBC’s Codex coding agent could have exposed sensitive GitHub authentication tokens through a command injection flaw, according to a new report out today from ...

In short:Security researcher Aonan Guan hijacked AI agents from Anthropic, Google, and Microsoft via prompt injection attacks on their GitHub Actions integrations, stealing API keys and tokens in each ...

The crime, it seems, was the uploading of public code to a public repository, Github. The code, which was publicly available here but now seems to be locked, is considered Flash Network’s proprietary ...