25 casos · pág. 1/2
A SafeDep researcher describes an experiment that uses Gryph (an audit trail for AI coding agents) and TypeSafe AI's Jev model to separate a developer's normal agent activity from attacks. The article cites threats to agents such as Claude Code and Codex: the Mini Shai-Hulud worm commits Claude Code hooks into repositories, malicious npm …
The open-source AI coding agent OpenCode disclosed a breach tied to a "large-scale distillation attack" that exposed stored external-provider API keys for 1.4% of OpenCode Console users. Affected users had linked providers such as Anthropic, OpenAI and Google. Users reported unauthorized charges ranging from several hundred USD to more th…
An attacker pushed forged commits to the default branches of two unrelated GitHub projects, hugo-paper and mevn-cli. The commits add a preinstall hook (scripts/preinstall.js) that downloads and silently runs a second-stage script from buildwithknexus.xyz during npm install or bun install. The commits copy the author, date and message of t…
Aikido Security published a best-practices guide for defending against software supply chain attacks. It cites Aikido Intel data: about 7.5 million package versions analyzed in Q2 2026, with 19,500 malicious packages confirmed. The guide uses recent incidents to show which controls would have worked: the axios compromise, tj-actions/chang…
Symantec's Threat Hunter Team reports that new versions of the Aoki infostealer now target credential and session files used by AI coding assistants. Earlier versions focused on browser, cryptocurrency wallet and password manager data. Aoki is a relatively new and sparsely documented stealer, first observed earlier in 2026, and its AI-rel…
GhostAction has returned with an expanded credential-theft operation. By October 9, 2026, attackers had injected malicious GitHub Actions workflows into 790 repositories, according to OpenSourceMalware's validated total. The campaign was first documented by GitGuardian in 2025 (817 repositories, 3,325 stolen secrets). It relies on comprom…
SafeDep analyzed sckit (the "supplychain.local worm"), a previously unreported cross-platform Go implant framework found on September 23, 2026 in the compromised MemTensor packages @memtensor/email protected (npm) and email protected (PyPI). It harvests credentials from developer machines and CI jobs, takes signed tasks from a C2 server, …
The npm account dirtyblanket published nine typosquatted packages on September 29, 2026 in 33 minutes, eight copying Express and one copying React. On Linux, a preinstall hook fetches node.js through the Internet Archive Wayback Machine, which pulls the worm linux.sh from Codeberg and runs it with bash. The worm installs CHAOS, an open-so…
In September 2026, researchers reported an attack that began inside a live AI coding assistant session at a software company. The attacker gained control of a developer's session, and the assistant recommended a PyPI package that looked normal. The developer installed it, and a hidden infostealer took source code, repository secrets and h…
The threat actor behind the GhostAction supply chain campaign has expanded beyond malicious GitHub Actions workflows. According to OpenSourceMalware, it now phishes open-source maintainers and plants a second-stage credential stealer disguised as a font file. The shift appears to follow GitHub's October 9 block on the malicious workflow, …
Between 19 and 22 October 2026, an operator published 15 npm packages whose names end in testmetest, carrying a Miasma-family self-propagating worm. The malicious versions steal credentials, spread to other packages and repositories, and install a wiper that deletes the victim's home directory when the stolen GitHub token is revoked. Safe…
A vendor-sponsored analysis by Exaforce (published on bleepingcomputer.com) says attackers are enumerating or exfiltrating data within about 15 minutes of gaining access. It describes three patterns: stolen developer GitHub OAuth tokens, ClickFix lures that impersonate Claude Code install instructions to deliver a macOS stealer, and help …
Check Point Research (CPR) analyzed Aokigahara, a newly observed infostealer seen in the wild that explicitly targets authentication files, session data and configuration files of AI applications and developer tools. Targeted tools include Claude, ChatGPT Desktop, Codex, Cursor, Windsurf, GitHub Copilot, Gemini CLI and JetBrains AI Assist…
On October 21, attackers published a malicious LiteLLM version 1.107.0 to PyPI and Docker Hub. LiteLLM is a widely used open source proxy for routing requests across LLM providers. The packages were live for about three hours and were downloaded an estimated 49,000+ times before being removed or repointed to clean artifacts. They install …
SafeDep reports that the PolinRider loader family now resolves its C2 servers from Ethereum mainnet. The loader reads small transactions from operator wallets and decodes the recipient address as an IP:port. SafeDep confirmed 35 GitHub repositories carrying the loader at HEAD on 2026-09-30 (7,578 stars and 2,884 forks combined). The inves…
Check Point Research describes Aokigahara, a newly observed Windows infostealer that may have appeared in earlier versions as Kamidere or Stygian. It combines standard theft of browser, cryptocurrency wallet, VPN, FTP/SFTP, password manager and email data with a dedicated aisessions handler. That handler collects authentication, session a…
SafeDep identified a malicious tensorlake npm release, version 0.5.144 (about 106,000 monthly downloads), that ran a Mini Shai-Hulud worm on install. It was published at 01:12:07 UTC on 8 October and flagged by SafeDep eight minutes later. The attacker used a repository administrator account to commit the payload to main through the GitHu…
OpenCode, the open-source AI agent framework developed by Anomaly, confirmed on October 17 a security breach that occurred the night before and affected its Console service. Console stores each workspace's third-party AI provider credentials centrally. About 1.4% of Console users, those with external providers linked, may have had OpenAI,…
F5 Labs published its March 2026 CASI Leaderboard update, which is now dominated by OpenAI and Anthropic. Z.ai's GLM-5 performs well on price and capability but has a weak security posture (CASI 37.56 vs 96.61 for Claude Opus 4.6 and 92.58 for GPT-5.2). The report also spotlights Sugar-Coated Poison (SCP), a multi-turn technique that grad…
This SentinelOne weekly roundup (Week 41, 2026) covers law enforcement actions, a phishing campaign and an actively exploited vulnerability. The most urgent item is CVE-2026-21589, a critical (CVSS 9.3) unauthenticated arbitrary file access flaw in Atlassian Data Center products. Exploitation attempts began about two hours after a public …
