A newly disclosed flaw in the way OpenAI, Anthropic, and Google carried hidden AI reasoning between API calls let researchers recover internal reasoning and secrets from session logs, including API keys and passwords. The weakness affected encrypted reasoning objects used by the providers' reasoning APIs, where a block created in one session could be replayed into another and, during testing,
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.
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.
Google deleted three AI agent workflows from its Agent Development Kit (ADK) Python repository. Pillar Security showed that a public GitHub issue could manipulate a triage agent into triggering a privileged code-fixing agent. The researchers said the public agent could be prompt-injected into posting /adk-issue-fix as adk-bot. They identified the bot as a collaborator, so that comment satisfied the privileged workflow's owner, member, or collaborator gate. The trusted bot identity became the authorization bridge. The team demonstrated arbitrary code execution on the continuous integration (CI) runner and exfiltration of the bot personal access token (PAT). The privileged job also held a Google API key and a Google Cloud service-account credential. Its researcher-controlled proof-of-concept attacks do not identify in-the-wild exploitation or a compromised ADK release.
Confirm this action.
Leaving now will discard your changes.