Tag: EN

LLM07: System Prompt Leakage – FireTail Blog

Sep 30, 2025 – Lina Romero – In 2025, AI is everywhere, and so are AI vulnerabilities. OWASP’s Top Ten Risks for LLMs provides developers and security researchers with a comprehensive resource for breaking down the most common risks to…

MegaSys Enterprises Telenium Online Web Application

View CSAF 1. EXECUTIVE SUMMARY CVSS v4 9.3 ATTENTION: Exploitable remotely/low attack complexity Vendor: Megasys Enterprises Equipment: Telenium Online Web Application Vulnerability: OS Command Injection 2. RISK EVALUATION Successful exploitation of this vulnerability could allow an unauthenticated attacker to inject…

Festo Controller CECC-S,-LK,-D Family Firmware

View CSAF 1. EXECUTIVE SUMMARY CVSS v3 9.8 ATTENTION: Exploitable remotely/low attack complexity Vendor: Festo Equipment: Controller CECC-S,-LK,-D Family Firmware Vulnerabilities: Exposure of Resource to Wrong Sphere, Untrusted Pointer Dereference, NULL Pointer Dereference, Files or Directories Accessible to External Parties,…

OpenPLC_V3

View CSAF 1. EXECUTIVE SUMMARY CVSS v4 6.1 ATTENTION: Low attack complexity Vendor: OpenPLC_V3 Equipment: OpenPLC_V3 Vulnerability: Reliance on Undefined, Unspecified, or Implementation-Defined Behavior 2. RISK EVALUATION Successful exploitation of this vulnerability could cause a denial of service, making the…

Festo CPX-CEC-C1 and CPX-CMXX

View CSAF 1. EXECUTIVE SUMMARY CVSS v3 7.5 ATTENTION: Exploitable remotely/low attack complexity Vendor: Festo Equipment: CPX-CEC-C1 and CPX-CMXX Vulnerability: Improper Privilege Management 2. RISK EVALUATION Successful exploitation of this vulnerability could allow unauthenticated, remote access to critical webpage functions…

Festo SBRD-Q/SBOC-Q/SBOI-Q

View CSAF 1. EXECUTIVE SUMMARY CVSS v3 8.2 ATTENTION: Exploitable remotely/low attack complexity Vendor: Festo Equipment: SBRD-Q/SBOC-Q/SBOI-Q Vulnerabilities: Incorrect Conversion between Numeric Types, Out-of-bounds Read, Reachable Assertion 2. RISK EVALUATION Successful exploitation of these vulnerabilities may allow the attacker to…

Defending LLM applications against Unicode character smuggling

When interacting with AI applications, even seemingly innocent elements—such as Unicode characters—can have significant implications for security and data integrity. At Amazon Web Services (AWS), we continuously evaluate and address emerging threats across aspects of AI systems. In this blog…