Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

Salt Labs recently showed that a single email could hijack the AI agent platform Manus and reach a victim’s connected accounts. The full technical breakdown, with complete evidence, payloads, and screenshots, is in our research team’s write-up, and Dark Reading first reported the finding in an exclusive. This post is the shorter version: what the finding means and what it tells every organization now deploying AI agents. For the full technical detail, read the Salt Labs research blog.

Salt Labs found that the agentic AI platform Manus could be hijacked with a single email. By hiding malicious instructions inside an ordinary message, researchers got Manus to execute malicious code and, from there, reach the email, cloud storage, and code repository accounts a user had connected to it. The full attack required nothing from the victim beyond asking Manus to check their inbox. No stolen password, no clicked link.

Your first login to a Red Hat OpenShift cluster can feel like sitting in an unfamiliar cockpit: dozens of menus, two perspectives, and dashboards full of metrics you haven’t learned to read yet. The OpenShift Console pulls all of it into one browser-based interface, so you can see what’s running, fix what’s broken, and deploy what’s next without memorizing a single oc flag command.

Co-founder and CCO We shipped bots in the LimaCharlie AI Terminal. You can create one in a few minutes: give it a role, pick a profile if you want one, and open a chat. I said this during our September Build Log demo and I'll repeat it here, because everything else in this post follows from it. The bot is the easy part.

With PoSA v1.11, we focused on a practical problem: detecting more attack activity does not necessarily help fraud and security teams make better decisions. PoSA already identifies activity across digital impersonation, credential theft, attacker devices and account access. The challenge is making the connections between that activity easier to understand, identifying which users and devices require attention, and making that intelligence available to the systems and teams responsible for responding.

Being part of the cybersecurity community means more than simply following the news or reading security research. It is about getting involved, having conversations, sharing experiences, discussing problems, and learning from peers who face similar operational challenges. Of course, all of this comes with an investment of time, energy, and a full day of travel to reach one of the world’s largest hacking conferences: DEF CON in Las Vegas.

Security leaders at key financial institutions in Singapore now have a new line in their compliance calendars: AI-assisted red teaming, a requirement MAS introduced on 1 July 2026. What appears to be a scoping exercise actually asks a harder question, i. e., how does a bank differentiate between another convincing report and one that secures the institution?

On September 1, 2026, OpenAI announced that its Astra model had reached the Critical tier for cyber capability under the company’s Preparedness Framework, a first for its systems. While working through an internal benchmark of 20 recently disclosed vulnerabilities in Google’s V8 engine, the model found two zero-days that no one had asked it to look for and used them in a working exploit chain. OpenAI is disclosing both flaws and restricting the capability to vetted testers.

Let’s catch up on the more interesting vulnerability disclosures and cyber security news gathered from articles across the web this week. This is what we have been reading about on our coffee break! Lucky find for him then!

WordPress patched CVE-2026-87902 on September 22, 2026. Attackers were exploiting it the same day. Within hours of disclosure, attackers progressed from reconnaissance to active exploitation attempts, including attempts to write malicious PHP files to disk. The vulnerability is critical, with a CVSS v4.0 score of 9.2. Unauthenticated attackers can exploit it remotely. A public scanning template is already in circulation, and CISA has added the vulnerability to its KEV catalog.