PulseAugur
EN
LIVE 23:20:29

Microsoft packages compromised twice with credential-stealing AI malware

By PulseAugur Editorial · [3 sources] ·

Microsoft's official open-source packages have been compromised for the second time in recent weeks, with malicious code designed to steal credentials being injected into 73 packages. This code activates when developers use AI coding agents to open the packages, potentially compromising systems by stealing tokens for cloud providers like AWS, Azure, and GCP, as well as password managers and developer tools. The attack, linked to threat actor TeamPCP and using malware known as Miasma, bypasses repository build pipelines by leveraging legitimate Microsoft OIDC tokens. AI

IMPACT Compromised AI development tools and packages pose a significant risk to the security of AI projects and infrastructure.

RANK_REASON This cluster describes a security incident involving compromised software packages, not a new AI model release or core AI research.

Read on Ars Technica — AI →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

Microsoft packages compromised twice with credential-stealing AI malware

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
This cluster describes a security incident involving compromised software packages, not a new AI model release or core AI research.
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
safety, product, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
110 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

Full methodology in our editorial standards.

COVERAGE [3]

  1. Ars Technica — AI TIER_1 English(EN) · Dan Goodin ·

    For the 2nd time in weeks, Microsoft packages laced with credential stealer

    73 packages run self-replicating stealer as soon as they're opened by an AI agent.

  2. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    For the second time in weeks, Microsoft packages have been found laced with credential-stealing code designed to activate when developers open them in AI coding

    For the second time in weeks, Microsoft packages have been found laced with credential-stealing code designed to activate when developers open them in AI coding agents. 73 packages were blocked on GitHub, executing a payload that steals credentials from AWS, Azure, GCP, Kubernete…

    LINKS arstechnica.com/…/for-the-2nd-time-in-wee… arstechnica.com/…/2026
  3. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    For the 2nd time in weeks, # Microsoft packages laced with # credential stealer Dozens of # cryptographically verified # opensource packages from Microsoft were

    For the 2nd time in weeks, # Microsoft packages laced with # credential stealer Dozens of # cryptographically verified # opensource packages from Microsoft were # compromised late last week to add advanced credential-stealing code that was triggered when # developers opened them …

    LINKS arstechnica.com/…/for-the-2nd-time-in-wee… arstechnica.com/…/2026

RELATED ENTITIES

RELATED TOPICS