Loading story…
Security researchers have highlighted the risks associated with 'Excessive Agency' vulnerabilities in Large Language Models (LLMs), where granting AI systems excessive permissions or autonomy can enable attackers to exploit internal APIs, invoke unauthorized plugins, or perform unintended actions such as SSRF attacks and unauthorized interactions with business applications. These vulnerabilities arise when LLMs are given more control than necessary, often without sufficient human oversight or intervention mechanisms, leading to critical and high-severity security risks in environments where AI agents are integrated with sensitive systems.
In response to the unique challenges posed by agentic AI, the Open Worldwide Application Security Project (OWASP) has introduced the AI Vulnerability Scoring System (AIVSS), a new framework designed to assess and manage vulnerabilities specific to AI and agentic systems. Unlike traditional models such as CVSS, AIVSS accounts for the non-deterministic and dynamic nature of AI, including issues like ephemeral identities and the need for privilege management in autonomous agents. The AIVSS provides structured risk assessment guides and a scoring tool to help organizations quantify and address AI-specific security risks that are not adequately covered by existing vulnerability frameworks.
Mallory correlates global threat intelligence with your attack surface — know if you’re exposed before adversaries strike.
2 events from the most recent confirmed update back to the earliest known activity.
An Infosec Writeups article described the OWASP LLM06 'Excessive Agency' issue, explaining how over-privileged LLMs and insecure plugin access can be abused to trigger unauthorized actions such as API calls, data access, account changes, or emails. The piece also outlined mitigations including least privilege, isolation of sensitive functions, human oversight, and monitoring of LLM-initiated actions.
At OWASP Global AppSec, a new scoring system for AI vulnerabilities was unveiled, marking a development in how AI security issues may be assessed and prioritized. The reference does not provide further implementation details or a more specific event date.
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
3 references tracked. Mallory keeps watching after this page renders.
infosecwriteups.com
Open sourceinfosecwriteups.com
Open sourcescworld.com
Open sourceMap indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
AI-powered tools from major technology companies such as Google and OpenAI are increasingly being used to discover vulnerabilities in open-source software, leading to a surge in bug reports for projects maintained largely by volunteers. While these AI systems, like Google's Project Naptime and OpenAI's Aardvark, have successfully identified significant flaws—including a critical vulnerability in OpenSSL (CVE-2024-9143) and a stack buffer underflow in SQLite—the volume and complexity of AI-generated reports are overwhelming open-source maintainers, many of whom lack the resources to address the influx, especially when reports lack accompanying patches. The issue has prompted discussion within the open-source and security communities about the need for new frameworks and scoring systems tailored to AI-discovered vulnerabilities. At the 2025 OWASP Global AppSec USA conference, experts highlighted the limitations of traditional vulnerability scoring models like CVSS for AI-related threats and previewed the development of the OWASP AI Vulnerability Scoring System (AIVSS). This initiative aims to address the unique, non-deterministic risks posed by AI in software security, underscoring the growing recognition that AI-driven vulnerability discovery requires new approaches to risk management and remediation.
Jul 4, 2026
Organizations are rapidly integrating AI into software development pipelines, with AI-generated code now present in every surveyed environment and a significant portion of codebases produced by AI tools. Security leaders report increased risk due to limited visibility into where and how AI is used, the proliferation of shadow AI, and the introduction of logic flaws or insecure patterns by autonomous agents. The lack of oversight and formal controls over AI-generated code and tools has expanded the attack surface, making product security and supply chain integrity top priorities for 2026. Industry experts emphasize the need for responsible adoption of AI-driven security tools, highlighting the importance of evaluation, deployment, and governance to maintain control and transparency. New frameworks, such as the AI Vulnerability Scoring System (AIVSS), are being developed to address the unique, non-deterministic risks posed by agentic and autonomous AI systems, which traditional models like CVSS cannot adequately capture. The shift to runtime application security and the management of non-human identities further underscore the evolving landscape, as organizations seek to balance innovation with robust security practices.
Jul 2, 2026
The Open Web Application Security Project (OWASP) has published its inaugural "Top 10 for Agentic Applications," a risk framework specifically addressing the unique security challenges posed by advanced AI agents. These agents, which go beyond simple chatbots to autonomously access data, use tools, and execute tasks, introduce new attack surfaces and risks such as agent goal hijacking, tool misuse, and privilege abuse. The list was developed with input from over 100 security researchers and validated by experts from organizations like NIST and the European Commission, and is based on real-world incidents where AI agents have been manipulated to exfiltrate data, misuse tools, or cause cascading failures in enterprise workflows. Security experts highlight that the rise of agentic AI also exposes previously overlooked vulnerabilities, such as shadow APIs and legacy systems that were once considered secure by obscurity. AI agents are capable of discovering and interacting with undocumented or forgotten APIs, making even antiquated systems vulnerable if they are connected to modern networks. The new OWASP framework underscores the urgent need for organizations to reassess their security postures, increase visibility into internal systems, and proactively address the risks introduced by autonomous AI agents and their ability to exploit both new and legacy infrastructure.
Jun 29, 2026