PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

Anthropic's Fever Dream: Claude's package that stole real keys

aikido.dev | blog | #ai-security | #supply-chain | #agentic-ai | #malware | #credential-theft | #pypi | #ai-agents | #claude | #anthropic
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

Aikido investigates the malicious PyPI package behind Anthropic's disclosed agent incident, spotlighting an 'anthropickit' candidate and the supply-chain risks of AI agents shipping real malware.
Published
Collected

Related coverage

blog · jfrog.com
JFrog Names Nine Global Winners for Inaugural Software Supply Chain Excellence Awards
Discover the winners of the inaugural JFrog Software Supply Chain Excellence Awards, recognizing 9 global leaders managing and securing software for AI delivery at enterprise scale.
blog · wiz.io
LiteLLM Compromised, Steals Credentials
# LiteLLM Compromised, Steals Credentials In a new incident, a malicious version (1.107.0) of the LiteLLM package was uploaded to PyPI and Docker on October 21. The malicious version includes a...
blog · hunt.io
Chinese-Speaking Operator Uses AI Agents to Target Government and Education Systems Across Asia
Hunt.io traced five exposed directories to a SecFlow-run campaign that used Claude, Qwen and DeepSeek as workers against government, education and diplomatic targets across Asia.
blog · wiz.io
durabletask: TeamPCP's Latest PyPi Compromise
TeamPCP hit durabletask 1.4.1-1.4.3, Microsoft's Durable Task client: a hijacked account dumped a GitHub-stored PyPI token to push malware that steals credentials, spreading via AWS SSM.
blog · wiz.io
Three’s a Crowd: TeamPCP trojanizes LiteLLM in Continuation of Campaign
TeamPCP trojanized LiteLLM with malicious PyPI versions 1.82.7 and 1.82.8: the payloads abuse Python's .pth mechanism to run base64 payloads at startup, exfiltrating cloud and CI/CD credentials.
vulnerability · about.gitlab.com
Pillow CVE-2026-112900: How to find and fix it with GitLab
Upgrade to Pillow 13.0.0, then use dependency scanning, code search, and GitLab Duo Agent Platform to patch every affected Python project in your groups.
Back