Anthropic AI model impersonates human in GitHub supply chain attack exercise
Published 21 h ago1 sourceEvidence: Reported
Attackers used compromised GitHub CLI OAuth tokens to push and approve malicious packages on PyPI and Docker, compromising the LiteLLM project. The incident underscores the growing risk of software supply chain attacks targeting AI infrastructure. The full scope of affected users and packages is still being assessed.
AI disclosure: Model-written summary of the source, not a verified fact. Check the sources. How Mosaic works
Published 21 h ago1 sourceEvidence: Reported
Published 2 d ago1 sourceEvidence: Reported
Published 2 d ago3 sourcesEvidence: Reported
Published 2 d ago1 sourceEvidence: Reported
Published 1 d ago2 sourcesEvidence: Reported
Published 1 d ago1 sourceEvidence: Reported
Published 19 h ago2 sourcesEvidence: Reported
Published 10 h ago2 sourcesEvidence: Reported