InfoSecBulletin Cybersecurity for mankind
A new vulnerability scoring system, the AI Vulnerability Scoring System (AIVSS), has been announced. It aims to address shortcomings of traditional models like the Common Vulnerability Scoring System (CVSS) that cannot effectively evaluate the complexity of modern AI technologies.
AI security expert Ken Huang introduced the AIVSS framework, noting that CVSS is inadequate for evaluating vulnerabilities in autonomous AI systems.
Researchers show new technique to bypass AI safety guardrails in Grok and Gemini
About thousands of leaked AWS keys Held Full Admin Rights
US Bank investigates LockBit’s Data Breach Claims
Five new malware families actively targeting Asian Gov.t infra
T-Mobile Cuts Cables to Remove Chiness Salt Typhoon Hackers from Network
Splunk, Zyxel Patch Multiple Flaws Enabling RCE and Root Command Execution
“Zombie Card” attack revels expired Visa card may be used for contactless payments
Critical Zimbra RCE Flaw Actively Exploited in the Wild
Operation CameraSwarm
A single hacker compromise 1400+ Dahua camera worldwide
Cl0p Ransomware Listed 40+ Victims of PTC Windchill Campaign
“The CVSS and other regular software vulnerability frameworks are not enough,” Huang explained. “These assume traditional deterministic coding. We need to deal with the non-deterministic nature of Agentic AI.”
Huang co-leads the AIVSS project with notable cybersecurity and academic leaders, like Zenity CTO Michael Bargury, AWS Engineer Vineeth Sai Narajala, and Stanford’s Information Security Officer Bhavya Gupta.
The group has worked with the Open Worldwide Application Security Project (OWASP) to create a framework for evaluating AI security threats in a structured and measurable way.
A New Approach to AI Vulnerability Scoring:
The AI Vulnerability Scoring System modifies the CVSS model by adding new parameters for AI systems. It starts with a base CVSS score and adds an evaluation of agentic capabilities, considering autonomy and tool use, which can increase risks. The final vulnerability score is obtained by averaging this combined score and adjusting it for the environmental context.
A dedicated portal at aivss.owasp.org offers documentation, guides for AI risk assessment, and a scoring tool for assessing AI vulnerability scores.
Huang highlighted a critical difference between AI systems and traditional software: the fluidity of AI identities. “We cannot assume the identities used at deployment time,” he said. “With agentic AI, you need the identity to be ephemeral and dynamically assigned. If you really want to have autonomy, you have to give it the privileges it needs to finish the task.”
Top Risks in Agentic AI Systems:
The AIVSS project has also identified the ten most severe core security risks for Agentic AI, though the team has refrained from calling it an official “Top 10” list. The current risks include:
Agentic AI Tool Misuse
Agent Access Control Violation
Agent Cascading Failures
Agent Orchestration and Multi-Agent Exploitation
Agent Identity Impersonation
Agent Memory and Context Manipulation
Insecure Agent Critical Systems Interaction
Agent Supply Chain and Dependency Attacks
Agent Untraceability
Agent Goal and Instruction Manipulation
Each of these risks reflects the interconnected and compositional nature of AI systems. As the draft AIVSS document notes, “Some repetition across entries is intentional. Agentic systems are compositional and interconnected by design. To date, the most common risks such as Tool Misuse, Goal Manipulation, or Access Control Violations, often overlap or reinforce each other in cascading ways.”
Huang provided an example of how this manifests in practice: “For tool misuse, there shouldn’t be a risk in selecting a tool. But in MCP systems, there is tool impersonation, and also insecure tool usage.”
