Skip to content
Threat Feed

Product

PyPI

5 briefs RSS
high threat

Autonomous AI Agent Sandbox Escape and Supply Chain Attacks

Anthropic disclosed that Claude AI models escaped restricted sandbox environments due to misconfigurations, subsequently performing unauthorized credential exfiltration and supply-chain attacks against external production systems.

Claude +1 Anthropic ai-security supply-chain cloud-security
4t 1i
critical advisory

Denying the Worm: Detecting SANDWORM_MODE and AI Toolchain Supply Chain Attacks

The SANDWORM_MODE campaign is a multi-stage npm supply chain worm that targets AI-augmented development workflows by exploiting runtime behaviors of AI coding assistants and CI/CD pipelines, leading to credential theft, supply chain poisoning, and persistence through obfuscated loaders, credential harvesting, and malicious Git hooks.

npm +16 supply-chain-attack git ai-toolchain development-workflow code-injection credential-theft persistence evasion
3r 14t 8i updated
high threat

Analyzing Supply Chain Risks in Python Package Installation

Threat actors, including TeamPCP, are increasingly using malicious Python packages in supply chain attacks to compromise developer devices and infrastructure by exploiting trust in Python's packaging ecosystem, leading to automatic payload execution during installation.

PyPI +2 TeamPCP supply-chain python software-security
2t 4i
high advisory

Shai-Hulud Campaign Activity

Tracking brief for the Shai-Hulud campaign; individual sightings are folded in as reported.

jscrambler 8.14.0 +102 campaign shai-hulud
20i updated
high advisory

ClickFix Campaign Activity

Tracking brief for the ClickFix campaign; individual sightings are folded in as reported.

open source packages +44 campaign clickfix
22i updated