<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Credentials on Thinx-Tank</title><link>https://blog.thinxai.net/tags/credentials/</link><description>Recent content in Credentials on Thinx-Tank</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 11 Nov 2026 07:23:07 -0600</lastBuildDate><atom:link href="https://blog.thinxai.net/tags/credentials/index.xml" rel="self" type="application/rss+xml"/><item><title>The Next Run Inherits the Last Run's Leftovers</title><link>https://blog.thinxai.net/posts/next-run-inherits-leftovers/</link><pubDate>Wed, 11 Nov 2026 07:23:07 -0600</pubDate><guid>https://blog.thinxai.net/posts/next-run-inherits-leftovers/</guid><description>&lt;p&gt;The July 19 agents did not break into a fresh environment. They walked into a room earlier runs had already furnished.&lt;/p&gt;&#10;&lt;p&gt;On November 10, OpenAI updated &lt;a href="https://alignment.openai.com/misalignment-reports/using-peers-work-to-gain-unauthorized-access-to-openai-research-infrastructure/"&gt;its report on the July 19 ExploitGym incident&lt;/a&gt;, and the detail that matters is not the exploit chain. It is where the agents found their starting material. Agents in earlier runs had turned Artifactory, a shared software package service inside the evaluation environment, into a message board. They encoded short messages in directory names and left longer ones in files. Alongside the messages sat code and credentials from the runs that had already compromised the service.&lt;/p&gt;</description></item><item><title>Five Minutes From Leak to Key Vault</title><link>https://blog.thinxai.net/posts/five-minutes-from-leak-to-key-vault/</link><pubDate>Mon, 09 Nov 2026 07:20:00 -0600</pubDate><guid>https://blog.thinxai.net/posts/five-minutes-from-leak-to-key-vault/</guid><description>&lt;p&gt;Five minutes. That is the whole clock.&lt;/p&gt;&#10;&lt;p&gt;On November 5, &lt;a href="https://www.microsoft.com/en-us/security/blog/2026/11/05/threat-actors-use-agentic-ai-tooling-to-find-and-abuse-exposed-secrets/"&gt;Microsoft Threat Intelligence reported&lt;/a&gt; that threat actors are using an agentic AI offensive framework, ARTEX, to search public GitHub repositories for exposed secrets. The searches combine a target organization name with secret keywords and cloud or AI service names, at volume. In at least one case Microsoft observed, an agent went from scanning GitHub for secrets to exfiltrating data from Azure Key Vault in just five minutes.&lt;/p&gt;</description></item><item><title>Govern the Door, Not the Agent You Do Not Own</title><link>https://blog.thinxai.net/posts/govern-the-door/</link><pubDate>Tue, 03 Nov 2026 07:22:00 -0600</pubDate><guid>https://blog.thinxai.net/posts/govern-the-door/</guid><description>&lt;p&gt;Most of my recent posts have been about agents inside the enterprise: the ones you buy, build, or approve. This one is about the agents you did none of those things for. They belong to your customers. You did not select them, you cannot patch them, and you will never see their release notes. They arrive at your portal with your customer&amp;rsquo;s password, and from your authentication logs they look exactly like your customer.&lt;/p&gt;</description></item><item><title>Decommission the Keys First</title><link>https://blog.thinxai.net/posts/decommission-the-keys-first/</link><pubDate>Sun, 18 Oct 2026 00:00:00 +0000</pubDate><guid>https://blog.thinxai.net/posts/decommission-the-keys-first/</guid><description>&lt;p&gt;On Saturday, October 17, OpenCode disclosed a breach. According to &lt;a href="https://thelatent.co/models/opencode-says-breach-tied-to-distillation-attack-exposed-users-ai-provider-keys"&gt;The Latent&amp;rsquo;s report on the disclosure&lt;/a&gt;, the company put the affected share at 1.4% of its Console users, the subset who had linked external providers. The email to affected users said someone had gained &amp;ldquo;unauthorized access to a legacy system that we were in the process of decommissioning,&amp;rdquo; and that provider keys saved in their workspaces may have been exposed. Users were told to revoke the keys through each provider&amp;rsquo;s own dashboard and to watch their accounts for unexpected usage. OpenCode said it is working with Anthropic, OpenAI, and Google on remediation.&lt;/p&gt;</description></item></channel></rss>