AI Agents Are Visiting Your Website. Which Ones Should You Trust?

The internet is changing fast. For years, the main goal of search was simple: to help users find links. A user searched, reviewed results, clicked a website, and consumed the content directly from the source. But AI is changing that model. Increasingly, users ask AI assistants for answers instead...

PT-2026-53959

Name of the Vulnerable Software and Affected Versions IBM Langflow OSS versions 1.0.0 through 1.9.6 Description An authenticated attacker can perform a Server-Side Request Forgery SSRF, which occurs when a server is tricked into making requests to an unintended location. The issue exists because...

Guardian Agents: The Next Layer of Identity Governance

AI agents are moving through enterprise environments, inheriting permissions, traversing systems, and executing decisions at machine speed with minimal oversight. The identity infrastructure built to govern human access wasn't designed for autonomous actors, and the gap between what enterprises a...

Dawn of the Apex Agentic Adversary

We are standing at the end of an era we never thought to mourn: the era of human-speed threats. For years, cybersecurity moved to a rhythm organizations could follow. A researcher found a bug, a CVE was cataloged, a vendor navigated a patch cycle, and weeks or even months later, a fix was deploye...

PT-2026-52028

Name of the Vulnerable Software and Affected Versions Warp versions 0.2025.10.08.08.12.stable 00 through 0.2026.05.06.15.42.stable 00 Description A command execution permission-check bypass exists in the default unsandboxed CLI agent profile. This profile is non-interactive and utilizes a command...

Agentic AI: The Weapon That No Longer Needs a Warrior

Every weapon begins as an extension of the hand that holds it. The spear lengthened the reach of the arm. The bow sent the point flying without the throw. The rifle placed a man's death a quarter mile beyond his sight, and the aircraft carried that death across oceans. At each turn, the distance...

Red-Teaming the Agentic Red-Team

The use of agentic systems to perform offensive security operations has moved from a theoretical possibility to a commoditized capability. However, while the community has focused on creating more and more capable agents, less attention has been allocated to assessing the security of those system...

This Week in Spring - June 23rd, 2026

Hi Spring fans! In this installment, we look at the wide and wonderful world of Spring, as usual, and there's a good amount to get to, fresh off the recent Spring Boot 4.1 generation release train, so let's dive right into it! I wrote a blog post looking at Spring Batch, MongoDB, and Spring Boot...

@claude-flow/plugin-agent-federation (>=1.0.0-alpha.9, <=1.0.0-alpha.15), @turtlepusher/plugin-agent-federation (>=1.0.0, <=1.0.1) +2 more potentially affected by CVE-2026-58195 via agentic-flow (>=2.0.2-alpha, <=2.0.12-fix.8)

agentic-flow NPM version =2.0.2-alpha, =1.0.0-alpha.9, =1.0.0, =0.5.0, =0.3.0, =0.3.1 Source cves: CVE-2026-58195 Source advisory: SNYK:JS-AGENTICFLOW-17818150...

Command Injection

Overview agentic-flow is a The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness planner/context/reviewer/retry/tool/memory/score policy and autonomously repairs code, then orches Affected version...

@claude-flow/plugin-agent-federation (>=1.0.0-alpha.9, <=1.0.0-alpha.15), @turtlepusher/plugin-agent-federation (>=1.0.0, <=1.0.1) +2 more potentially affected by CVE-2026-58195 via agentic-flow (>=2.0.2-alpha, <=2.0.12-fix.8)

agentic-flow NPM version =2.0.2-alpha, =1.0.0-alpha.9, =1.0.0, =0.5.0, =0.3.0, =0.3.1 Source cves: CVE-2026-58195 Source advisory: OSV:GHSA-VCV2-R9JH-99M5...

GHSA-VCV2-R9JH-99M5 Agentic-Flow: OS Command Injection in agentic-flow MCP server tools via unsanitized tool-parameter interpolation into execSync

Summary agentic-flow versions = 2.0.13 MCP server tools interpolated attacker-influenceable tool parameters e.g. agent, task, name, language, agentdb arguments directly into shell command strings passed to execSync. A malicious value reaching any of the affected MCP tools could break out of the...

MAL-2026-6095 Malicious code in oem-agentic-shared (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector f612eb2fa947323c936a0bb1becc602f0f837f9023edac22a945470566386a8c [email protected] is a hollow stub: index.js exports an empty object and package.json has empty author, empty description, and no real...

Aembit Extends IAM for Agentic AI to Microsoft Copilot Studio

Las Vegas, USA / Nevada, 16th June 2026, CyberNewswire...

Making secret scanning more trustworthy: Reducing false positives at scale

Secret scanning plays a critical role in protecting developers and organizations. It helps catch exposed credentials early and prevents small mistakes from turning into real incidents. At GitHub's scale, even small inefficiencies create real friction. Too many false positives make alerts harder t...

AI Security at Machine Speed: A Roadmap for Modern AppSec

With AI API calls set to grow 1,000x by 2027, you need a roadmap to secure your enterprise against agentic threats...

Assessing Automated Prompt Injection Attacks in Agentic Environments

Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effective for jailbreaking--remain underexplored in realistic agentic settings. We present a comprehensive empirical evaluation of automated prompt...

State of Agentic AI Security and Governance

An OWASP white paper analyzing the security, governance, and risk management considerations surrounding agentic AI systems, including autonomous decision-making, tool access, prompt injection, data protection, and organizational oversight. This is version 2.01...

CVE-2026-44246

nnU-Net is a semantic segmentation framework that automatically adapts its pipeline to a dataset. Prior to 2.4.1, the nnU-Net Issue Triage workflow in .github/workflows/issue-triage.yml is vulnerable to Agentic Workflow Injection. The workflow sets allowednonwriteusers: $...

Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us

In this article 1. Why the Taxonomy Needed Updating 2. Seven new failure modes 3. Operational findings: What red teaming showed 4. New mitigations 5. What to do this quarter When the Microsoft AI Red Team published the Taxonomy of Failure Modes in Agentic AI Systems in April 2025, the goal was a...