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...

CVE-2026-49194

The debugging routine SCREENCLICK5053 enables a connection to skip the standard device login prompt entirely and directly enter an interactive shell interface...

CVE-2026-49194

Technical details about CVE-2026-49194 are not publicly available in the provided documents; monitor for updates.

CVE-2026-49194 SCREEN_CLICK Authentication Bypass

The debugging routine SCREENCLICK5053 enables a connection to skip the standard device login prompt entirely and directly enter an interactive shell interface...

CVE-2026-2614

A flaw was found in mlflow. An unauthenticated remote attacker can exploit a vulnerability in the createmodelversion handler by including a specific tag, mlflow.prompt.isprompt, in a CreateModelVersion request. This bypasses source path validation, allowing the attacker to specify an arbitrary...

CVE-2026-45134

LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to LangSmith SDK Python 0.8.0 and JS/TS 0.6.0, the LangSmith SDK's prompt pull methods pullprompt / pullpromptcommit in Python, pullPrompt / pullPromptCommit in JS/TS fetch and deserialize prompt manifests from...

CVE-2026-42074 OpenClaude: Sandbox Bypass via Model-Controlled `dangerouslyDisableSandbox` Input

OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Prior to version 0.5.1, the dangerouslyDisableSandbox parameter is exposed as part of the BashTool input schema, meaning the LLM an untrusted principal per the project's own threat model can set ...

EUVD-2026-33972

OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Prior to version 0.5.1, the dangerouslyDisableSandbox parameter is exposed as part of the BashTool input schema, meaning the LLM an untrusted principal per the project's own threat model can set ...

CVE-2026-45312

RAGFlow is an open-source RAG Retrieval-Augmented Generation engine. In 0.24.0 and earlier, a Jinja2 template injection in the prompt generator rag/prompts/generator.py allows any authenticated user to execute arbitrary OS commands on the server. Any normal user can register, create a Canvas...

openSUSE 16 Security Update : putty (openSUSE-SU-2026:20851-1)

The remote openSUSE 16 host has a package installed that is affected by a vulnerability as referenced in the openSUSE- SU-2026:20851-1 advisory. Changes in putty: - Update to release 0.84 Fixed a remotely triggerable double-free in RSA key exchange. Fixed a remotely triggerable crash assertion...

CVE-2026-25879

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.63.0, SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database role that has privileges enabling code execution or filesystem access...

EUVD-2026-33830

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.63.0, SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database role that has privileges enabling code execution or filesystem access...

CVE-2026-25879

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.63.0, SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database role that has privileges enabling code execution or filesystem access...

CVE-2026-25879 Langroid has Prompt to SQL Injection, Leading to RCE

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.63.0, SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database role that has privileges enabling code execution or filesystem access...

CVE-2026-25879

Langroid's CVE-2026-25879 affects the Langroid framework (SQLChatAgent) prior to v0.63.0. An attacker who can shape input to the agent can cause LLM-provided SQL to execute dialect-specific primitives such as COPY ... FROM PROGRAM, enabling Remote Code Execution on the database host when the data...

CVE-2026-25879 Langroid has Prompt to SQL Injection, Leading to RCE

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.63.0, SQLChatAgent executes SQL produced by an LLM, which is influenceable by prompt injection. When configured with a database role that has privileges enabling code execution or filesystem access...

EUVD-2026-33750

CodexBar prior to 0.32.0 contains a privilege escalation vulnerability in the CLI installer that allows local attackers to execute arbitrary commands as root by exploiting a race condition in temporary file handling. The installer creates a temporary file with mktemp, writes a privileged shell...

-cascade-scan

cascade-scan AI Agent security evaluation framework — autom...

CVE-2026-10210

A vulnerability was found in AstrBotDevs AstrBot 4.23.6. Affected by this vulnerability is the function sanitizepromptdescription of the file astrbot/core/skills/skillmanager.py. The manipulation results in injection. The attack may be performed from remote. The exploit has been made public and...

EUVD-2026-33531

A vulnerability was found in AstrBotDevs AstrBot 4.23.6. Affected by this vulnerability is the function sanitizepromptdescription of the file astrbot/core/skills/skillmanager.py. The manipulation results in injection. The attack may be performed from remote. The exploit has been made public and...