“Sorry, I can’t help with that”: How your guardrails might become the attacker’s best friend

Welcome to this week's edition of the Threat Source newsletter. Hello, everyone. Long time reader, first time writer here at the Threat Source newsletter! I wanted to start out by introducing myself. My colleague and friend Mick Baccio set the bar pretty high last week, so I was planning to tell...

Grok fooled into stealing user chat, location data, and more

A new type of prompt injection attack shows why giving AI assistants access to browsers, code tools, and private data deserves extra caution. AI researchers describe "Cryptographic Context Injection"—an attack that hides malicious instructions inside encrypted data. The AI is then persuaded to...

The safety penalty: Reclaiming operational sovereignty in the age of AI

As frontier models advance in cyber capability, their guardrails also become more restrictive. Defenders relying on these models to power core SOC processes cannot afford to pay the "safety penalty" of being blocked by these safeguards. Organizations should monitor model refusal rates and use the...

MCP Server Security: The Blind Spot in Your AI Stack

Short version: an MCP server is the tooling layer that lets an AI agent act on external systems. Hosted remotely, it is an API endpoint like any other — and it needs bot and WAF controls in front of it, API security on its own endpoints, and AI guardrails that inspect what the tools send back, no...

CVE-2026-15044 Trustyai-service-operator: trustyai service operator: unauthenticated access to ai guardrails and orchestrator apis

A flaw was found in the TrustyAI Service Operator. When deploying services like gorch or NemoGuardrails, if a specific security setting is not enabled, these services can expose their communication channels without requiring users to prove their identity. This allows any other program within the...

Your Automated Pentest Looks Clean. See What It Missed in This Expert Webinar

Your pentest report looks clean. That might be the problem. Run automated pentesting long enough, and the new findings start to dry up. By the third or fourth run, fewer issues appear. The report looks stable. Leadership reads "stable" as "secure." It usually isn't. The work slows down. The risk...

Guardrails has an arbitrary code execution vulnerability

An arbitrary code execution vulnerability exists in versions 0.2.9 up to 0.5.10 of the Guardrails AI Guardrails framework because of the way it validates XML files. If a victim user loads a maliciously crafted XML file containing Python code, the code will be passed to an eval function, causing i...

CVE-2024-45858

An arbitrary code execution vulnerability exists in versions 0.2.9 up to 0.5.10 of the Guardrails AI Guardrails framework because of the way it validates XML files. If a victim user loads a maliciously crafted XML file containing Python code, the code will be passed to an eval function, causing i...

CVE-2024-45858

An arbitrary code execution vulnerability exists in versions 0.2.9 up to 0.5.10 of the Guardrails AI Guardrails framework because of the way it validates XML files. If a victim user loads a maliciously crafted XML file containing Python code, the code will be passed to an eval function, causing i...

CVE-2024-45858

An arbitrary code execution vulnerability exists in versions 0.2.9 up to 0.5.10 of the Guardrails AI Guardrails framework because of the way it validates XML files. If a victim user loads a maliciously crafted XML file containing Python code, the code will be passed to an eval function, causing i...

CVE-2024-45858: Improper Neutralization of Directives in Dynamically Evaluated Code

An arbitrary code execution vulnerability exists in versions 0.2.9 up to 0.5.10 of the Guardrails AI Guardrails framework because of the way it validates XML files. If a victim user loads a maliciously crafted XML file containing Python code, the code will be passed to an eval function, causing i...