Indirect Prompt Injection Attacks Against LLM Assistants

This piece highlights a recent study, “Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous,” which examines real-world vulnerabilities in large language model assistants like Gemini. The researchers define “Promptware” as maliciously crafted prompts embedded in everyday interactions—such as emails, calendar invites, or shared documents—that an assistant may interpret and act upon. They detail 14 distinct attack scenarios across five categories, including short-term context poisoning, permanent memory poisoning, misuse of tools, automatic agent invocation, and automatic app invocation. These attacks can trigger digital actions—spam, phishing, data leaks, disinformation—and even physical consequences like unauthorized control of smart-home devices. Their Threat Analysis and Risk Assessment (TARA) shows that 73 percent of these threats pose high or critical risk to users. However, the authors also demonstrate that the deployment of targeted mitigations—now already implemented by Google following disclosure—can reduce risk substantially, from very high to very low or medium levels. 

https://www.schneier.com/blog/archives/2025/09/indirect-prompt-injection-attacks-against-llm-assistants.html

Comments

Post a Comment

Popular posts from this blog

Secure Vibe Coding Guide: Best Practices for Writing Secure Code

Ken Huang's "Secure Vibe Coding Guide" emphasizes the importance of integrating security into the software development lifecycle. The guide provides best practices for writing secure code, including input validation, proper authentication mechanisms, and secure data storage techniques. It also highlights the necessity of regular code reviews and staying updated with the latest security vulnerabilities and patches. By following these guidelines, developers can create applications that are resilient against common security threats and contribute to a safer digital environment.  https://kenhuangus.substack.com/p/secure-vibe-coding-guide
Read more

KEVIntel: Real-Time Intelligence on Exploited Vulnerabilities

KEVIntel is a dynamic platform providing up-to-date information on known exploited vulnerabilities (KEVs). It aggregates data from over 50 public sources, including CISA, and enriches each entry with metadata such as EPSS scores, online mentions, scanner inclusion, and exploitation status. The platform aims to serve as an early warning system, offering insights even before official publications. KEVIntel supports various formats like JSON, CSV, and RSS, facilitating integration into security operations. These entries include CVSS scores, exploit status, and links to proof-of-concept code, aiding organizations in prioritizing remediation efforts.   https://kevintel.com/
Read more

OWASP SAMM Skills Framework Enhances Software Security Roles

The OWASP SAMM Skills Framework, introduced on February 9, 2025, is a new initiative donated by Siemens to enhance software security practices within organizations. This framework assigns specific responsibilities to SAMM (Software Assurance Maturity Model) streams, clarifying which roles are involved in advancing each stream. It provides guidance on the necessary skills and training for each role, aligning SAMM-related activities with appropriate stakeholders and their required competencies. This alignment helps organizations identify the right personnel and visualize shared responsibilities, ensuring a structured approach to secure product development. Implementing the OWASP SAMM Skills Framework involves several key steps. Organizations must first map responsibilities to roles, ensuring each task is assigned to the right individual. Next, they must evaluate and align stakeholders with specific SAMM streams, validating that those assigned understand and accept their roles in advanci...
Read more