Two malicious LiteLLM releases sat on PyPI for about 40 minutes in March carrying credential-stealing code capable of harvesting cloud keys, SSH keys, Kubernetes tokens, database passwords, and other secrets from systems that installed them. Threat intelligence firm CloudSEK now says a dataset it obtained, built from roughly 434,000 files the attackers captured, maps potential exposure to more
SAP has released patches to address a maximum-severity security flaw impacting Commerce Cloud (Data Hub Adapter) that could result in arbitrary code execution. The vulnerability, assigned the CVE identifier CVE-2026-58231, is rated 10.0 on the CVSS scoring system. It has been described as a case of insufficient authorization checks and input validation. "SAP Commerce Cloud allows an
LexisNexis took its Diligence, Metabase API, and Newsdesk services offline as part of its response to unusual activity on servers hosted and managed by an unnamed third-party vendor. This development is consistent with broader industry trends, where threat actors increasingly reuse proven techniques and commodity tooling rather than investing in novel malware. Security teams should review their detection rules, keep threat-intelligence feeds current, and validate that incident-response runbooks are tested before an incident occurs.
A GitHub issue opened by an account with no repository privileges was enough to execute code on the CI runners behind Anthropic's and Google's own coding-agent repositories. On OpenAI's, it was enough to hijack the next agent run. Novee Security ran the attack against each vendor's agent in the configuration that the vendor ships by default, and presented the work at Black Hat USA on August 5. Two CVEs came out of it. Both are patched. Gemini CLI carries the worst of the two. CVE-2026-12537 (CVSS 4 score: 10.0) is an OS command injection in the container launcher, reached through a crafted .gemini/.env file, which lets an unprivileged attacker run code on the host of a headless CI platform before the sandbox starts. It is fixed in Gemini CLI 0.39.1 and run-gemini-cli 0.1.22. In Claude Code, CVE-2026-54316 turned Hugging Face's public download counter into an exfiltration channel that leaked an API key one character at a time, and is fixed in 2.1.163. Every Claude Code release from 0.2.54 up to 2.1.163 is affected. Anthropic says exploitation required getting untrusted content into a Claude Code context.
Cisco has rolled out updates to address multiple critical security vulnerabilities impacting Catalyst SD-WAN and IOS XE Software as part of a comprehensive internal security review. The security issues affect Cisco Catalyst SD-WAN Software, regardless of device configuration, and Cisco IOS XE Software when it is running in autonomous or controller mode. "These vulnerabilities were found The reporting underscores the importance of treating third-party software and infrastructure as part of your own attack surface, since trust in a vendor is only as strong as the vendor’s own security posture. Beyond patching, organizations should inventory exposed services, disable unused functionality, and require multi-factor authentication wherever it can be deployed.
Cisco has rolled out updates to address multiple critical security vulnerabilities impacting Catalyst SD-WAN and IOS XE Software as part of a comprehensive internal security review. The security issues affect Cisco Catalyst SD-WAN Software, regardless of device configuration, and Cisco IOS XE Software when it is running in autonomous or controller mode. "These vulnerabilities were found during internal security testing using existing testing processes as well as frontier AI models [...] and are not known to be actively exploited," Cisco said, urging customers to apply the necessary updates for optimal protection. The vulnerabilities impacting Catalyst SD-WAN Software are listed below - The issues have been addressed in the following versions of Cisco Catalyst SD-WAN Software - The vulnerabilities impacting IOS XE Software relate to improper access control, command injection, and improper input validation -
Forescout found 22 internet-facing Rockwell Automation programmable logic controllers (PLCs) in cities hit by recent cyberattacks on US water utilities. Nineteen used the same mobile carrier network. Its August 3 scan counted 4,407 exposed Rockwell controllers worldwide, including 2,844 in the United States, but Forescout could not confirm any were compromised. That figure counts exposed Because attacks of this type can go unnoticed for extended periods, the window between initial compromise and detection is often the deciding factor in the eventual impact. Beyond patching, organizations should inventory exposed services, disable unused functionality, and require multi-factor authentication wherever it can be deployed.
Forescout found 22 internet-facing Rockwell Automation programmable logic controllers (PLCs) in cities hit by recent cyberattacks on US water utilities. Nineteen used the same mobile carrier network. Its August 3 scan counted 4,407 exposed Rockwell controllers worldwide, including 2,844 in the United States, but Forescout could not confirm any were compromised. That figure counts exposed controllers, not water utilities or confirmed victims. Forescout said the publicly described effects could be achieved without a vulnerability exploit: attackers changed IP addresses and set passwords on controllers that were already reachable, causing operators to lose visibility and, in some cases, control of connected equipment. Neither the government alerts nor Forescout's analysis explains how the attackers found, selected, or initially accessed their targets.
Security flaws in agent infrastructure from Amazon Web Services (AWS), Google, and Vercel let untrusted or forged instructions reach an agent's tools with no check that a model turn had authorized them. In several of the attack paths, the model never ran at all, so system prompts, content filters, and model-level guardrails never got a chance to intervene. The affected products include Amazon Because attacks of this type can go unnoticed for extended periods, the window between initial compromise and detection is often the deciding factor in the eventual impact. Security teams should review their detection rules, keep threat-intelligence feeds current, and validate that incident-response runbooks are tested before an incident occurs.
Security flaws in agent infrastructure from Amazon Web Services (AWS), Google, and Vercel let untrusted or forged instructions reach an agent's tools with no check that a model turn had authorized them. In several of the attack paths, the model never ran at all, so system prompts, content filters, and model-level guardrails never got a chance to intervene. The affected products include Amazon Bedrock AgentCore's InvokeHarness API, Google's Agent Development Kit (ADK) for Python, and the Vercel AI SDK harness packages for the Codex and OpenCode coding agents. AWS has fixed the managed service, Google addressed the issues in ADK 2.5.0, and Vercel patched @ai-sdk/harness-codex in version 1.0.29 and @ai-sdk/harness-opencode in version 1.0.28. These are not identical vulnerabilities and do not share the same attack conditions. AWS involved an authenticated remote request, Google's paths required attacker-controlled session events or user-authored function calls, and Vercel's flaws required untrusted code already running inside a Linux sandbox.
Confirm this action.
Leaving now will discard your changes.