Microsoft Agent Framework Releases Poisoned With Credential Stealer
Versions 1.26.1 and 1.26.2 of agent-framework on PyPI steal Azure, Azure DevOps, and GitHub Actions credentials when Python starts.
Made by GitHub. No known exploited vulnerabilities on record.
Versions 1.26.1 and 1.26.2 of agent-framework on PyPI steal Azure, Azure DevOps, and GitHub Actions credentials when Python starts.
Lab research shows how device code phishing, a technique that applies to any device-flow client, can extend to AI coding agents, using GitHub Copilot CLI as an illustrative example.
Two AI agents, separately over a five-day period, autonomously tried to access connected applications, including Google Calendar, Gmail, Slack, and GitHub, without account owner approval.
A new campaign dubbed 'wfx-loot' has unfolded on GitHub where threat actors used 4,837 compromised accounts to probe 61,764 repositories, open pull requests, and push secrets-stealing malware.
Using thousands of hijacked accounts, the wfx-loot campaign planted a CI secret stealer that ran in over 1,800 GitHub repositories.
A command in Claude Code inadvertently saves files with credentials and other sensitive data to public Git repositories, creating security gaps for organizations.
Cybersecurity professionals are being targeted with infected security projects on GitHub that deploy a backdoor and information stealer malware.
Microsoft Threat Intelligence has observed threat actors using the agentic offensive security framework ARTEX to search GitHub for OAuth application secrets, which can be used to compromise the associated OAuth application and perform authenticated actions in the application’s tenant. Agents operating on behalf of threat actors then used the compromised OAuth applications to perform a variety of subsequent actions…
A crypto-mining campaign abusing Hugging Face models returned days after takedown, hijacking GPU servers and planting backdoors, with one model downloaded over 28,000 times. Separately, a fake Solana starter kit on GitHub is positioned to trick AI coding agents into installing a NetSupport RAT.
The supply chain attack campaign's shift toward developer endpoints and cloud access signals what could be next for the cybercrime outfit.
An ongoing supply chain attack is harvesting credentials and sensitive data from thousands of developer repositories.
The model engaged in severe overreach and dishonesty, creating fake identities and submitting malicious code on GitHub.
Hackers used compromised GitHub CLI OAuth tokens to push and approve malicious packages on PyPI and Docker.
Attackers can steal credentials and begin exfiltrating data within minutes, often before security teams can respond. Exaforce examines real-world attacks involving stolen GitHub tokens, malicious AI installers, and MFA phishing, explaining why faster detection and automated containment are critical.
A developer's GitHub account that was compromised several months earlier was used to push malicious code to unsuspecting users.
French cloud and hosting provider OVHcloud is warning users that attackers compromised its open-source command-line interface (CLI) tool to distribute information-stealing malware.
Most of the affected individuals are Meta employees in the United States and they are being offered credit monitoring services.
More than 17,000 fake repositories on GitHub are distributing the SmartLoader malware after the FakeGit campaign reactivated earlier this month to push the StealC infostealer.
Analysis of Blinder Tunnel, an Iran-nexus campaign using fake Dubai Airports recruitment lures and GitHub C2 malware to target critical infrastructure.
Roughly 200,000 of the credentials were exposed after GitHub enabled push protections by default.
The latest developments from the last 30 days, newest first.
Microsoft Agent Framework Releases Poisoned With Credential Stealer
Basis: Reporting by SecurityWeek
The risks of device code authentication for AI coding agents
Basis: Microsoft Security Blog & MSRC (vendor advisory)
Grok Bots Attempt to Access Corporate Data Without User Approval
Basis: Reporting by Dark Reading
Hackers compromise 4,800 GitHub accounts to steal cloud credentials
Basis: Reporting by BleepingComputer
Attacker Targets 60,000 GitHub Repositories in Credential Theft Campaign
Basis: Reporting by SecurityWeek
AI Coding Agents Leak Thousands of Secrets to GitHub
Basis: Reporting by Dark Reading
Fake security tools on GitHub push backdoors and infostealers
Basis: Reporting by BleepingComputer
Threat actors use agentic AI tooling to find and abuse exposed secrets
Basis: Microsoft Security Blog & MSRC (vendor advisory)
6 earlier events are available with a subscription. See plans.