AI Agents and the Non‑Human Identity Crisis: How to Deploy AI More Securely at Scale

Artificial intelligence is driving a massive shift in enterprise productivity, from GitHub Copilot's code completions to chatbots that mine internal knowledge bases for instant answers. Each new agent must authenticate to other services, quietly swelling the population of non‑human identities NHI...

AI Agents and the Non‑Human Identity Crisis: How to Deploy AI More Securely at Scale

Artificial intelligence is driving a massive shift in enterprise productivity, from GitHub Copilot’s code completions to chatbots that mine internal knowledge bases for instant answers. Each new agent must authenticate to other services, quietly swelling the population of non‑human identities NHI...

AdInject: Real-World Black-Box Attacks on Web Agents Via Advertising Delivery

Vision-Language Model VLM based Web Agents represent a significant step towards automating complex tasks by simulating human-like interaction with websites. However, their deployment in uncontrolled web environments introduces significant security vulnerabilities. Existing research on adversarial...

A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?

Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical user interfaces. We are now witnessing the emergence of \emphComputer-Using Agents CUAs, capable of autonomously...

CoTGuard: Using Chain-Of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems

As large language models LLMs evolve into autonomous agents capable of collaborative reasoning and task execution, multi-agent LLM systems have emerged as a powerful paradigm for solving complex problems. However, these systems pose new challenges for copyright protection, particularly when...

CVE-2024-3334

A security bypass vulnerability exists in the Removable Media Encryption RMEcomponent of Digital Guardian Windows Agents prior to version 8.2.0. This allows a user to circumvent encryption controls by modifying metadata on the USB device thereby compromising the confidentiality of the stored data...

CVE-2023-32990

A missing permission check in Jenkins Azure VM Agents Plugin 852.v8d35f0960a43 and earlier allows attackers with Overall/Read permission to connect to an attacker-specified Azure Cloud server using attacker-specified credentials IDs obtained through another method...

CVE-2023-32988

A missing permission check in Jenkins Azure VM Agents Plugin 852.v8d35f0960a43 and earlier allows attackers with Overall/Read permission to enumerate credentials IDs of credentials stored in Jenkins...

Malware in com.unity.ml-agents

Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be rotated immediately from a different computer. The package should be removed, but as full control of the computer may have been given to an outsid...

Malicious code in com.unity.ml-agents (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware bfceda90642153626d064813e4c0c601ca81d18a6c5fd9e96855cbdee511db13 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

CVE-2022-36173

FreshService macOS Agent 4.4.0 and FreshServce Linux Agent 3.4.0 are vulnerable to TLS Man-in-The-Middle via the FreshAgent client and scheduled update service...

CVE-2022-24684

HashiCorp Nomad and Nomad Enterprise 0.9.0 through 1.0.16, 1.1.11, and 1.2.5 allow operators with job-submit capabilities to use the spread stanza to panic server agents. Fixed in 1.0.18, 1.1.12, and 1.2.6...

CVE-2022-41139

MITRE CALDERA 4.1.0 allows stored XSS via app.contact.gist aka the gist contact configuration field, leading to execution of arbitrary commands on agents...

CVE-2022-30950

Jenkins WMI Windows Agents Plugin 1.8 and earlier includes the Windows Remote Command library which has a buffer overflow vulnerability that may allow users able to connect to a named pipe to execute commands on the Windows agent machine...

CVE-2022-30951

Jenkins WMI Windows Agents Plugin 1.8 and earlier includes the Windows Remote Command library does not implement access control, potentially allowing users to start processes even if they're not allowed to log in...

CVE-2022-22544

Solution Manager Diagnostics Root Cause Analysis Tools - version 720, allows an administrator to execute code on all connected Diagnostics Agents and browse files on their systems. An attacker could thereby control the managed systems. It is considered that this is a missing segregation of duty f...

CVE-2021-44886

In Zammad 5.0.2, agents can configure "out of office" periods and substitute persons. If the substitute persons didn't have the same permissions as the original agent, they could receive ticket notifications for tickets that they have no access to...

CVE-2021-21627

A cross-site request forgery CSRF vulnerability in Jenkins Libvirt Agents Plugin 1.9.0 and earlier allows attackers to stop hypervisor domains...

CVE-2020-5754

Webroot endpoint agents prior to version v9.0.28.48 allows remote attackers to trigger a type confusion vulnerability over its listening TCP port, resulting in crashing or reading memory contents of the Webroot endpoint agent...

CVE-2020-5755

Webroot endpoint agents prior to version v9.0.28.48 did not protect the "%PROGRAMDATA%\WrData\PKG" directory against renaming. This could allow attackers to trigger a crash or wait upon Webroot service restart to rewrite and hijack dlls in this directory for privilege escalation...