Securing AI Agents against Prompt Injection Attacks

Retrieval-augmented generation RAG systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive benchmark for evaluating prompt injection risks in RAG-enabled A...

CVE-2025-54660

An active debug code vulnerability in Fortinet FortiClientWindows 7.4.0 through 7.4.3, FortiClientWindows 7.2.0 through 7.2.10, FortiClientWindows 7.0 all versions may allow a local attacker to run the application step by step and retrieve the saved VPN user password...

MalRAG: A Retrieval-Augmented LLM Framework for Open-Set Malicious Traffic Identification

Fine-grained identification of IDS-flagged suspicious traffic is crucial in cybersecurity. In practice, cyber threats evolve continuously, making the discovery of novel malicious traffic a critical necessity as well as the identification of known classes. Recent studies have advanced this goal wi...

CVE-2025-64706

Typebot is an open-source chatbot builder. In version 3.9.0 up to but excluding version 3.13.0, an Insecure Direct Object Reference IDOR vulnerability exists in the API token management endpoint. An authenticated attacker can delete any user's API token and retrieve its value by simply knowing th...

CVE-2025-9982

CVE-2025-9982 affects QuickCMS 6.8. The vulnerability is due to sensitive admin credentials hardcoded in a plaintext configuration file, allowing attackers with access to the source code or server filesystem to retrieve credentials and potentially escalate privileges. Only version 6.8 was tested ...

EUVD-2025-175346

Typebot is an open-source chatbot builder. In version 3.9.0 up to but excluding version 3.13.0, an Insecure Direct Object Reference IDOR vulnerability exists in the API token management endpoint. An authenticated attacker can delete any user's API token and retrieve its value by simply knowing th...

smc: Use __sk_dst_get() and dst_dev_rcu() in in smc_clc_prfx_set().

...

Typebot 安全漏洞

Typebot is an open source chatbot builder by the individual developer Baptiste Arnaud. A security vulnerability exists in Typebot version 3.9.0 up to and including version 3.13.0, which stems from the presence of an insecure direct object reference in the API token management endpoint, which coul...

EUVD-2025-124915

In the Linux kernel, the following vulnerability has been resolved: smc: Use skdstget and dstdevrcu in smcclcprfxmatch. smcclcprfxmatch is called from smclistenwork and not under RCU nor RTNL. Using skdstgetsk-dev could trigger UAF. Let's use skdstget and dstdevrcu. Note that the returned value o...

CVE-2025-40168 smc: Use __sk_dst_get() and dst_dev_rcu() in smc_clc_prfx_match().

In the Linux kernel, the following vulnerability has been resolved: smc: Use skdstget and dstdevrcu in smcclcprfxmatch. smcclcprfxmatch is called from smclistenwork and not under RCU nor RTNL. Using skdstgetsk-dev could trigger UAF. Let's use skdstget and dstdevrcu. Note that the returned value o...

CVE-2025-12903

The CVE-2025-12903 concerns the WordPress plugin Payment Plugins Braintree For WooCommerce. It affects all versions up to 3.2.78 and arises from a missing capability check on the REST endpoint wc-braintree/v1/3ds/vaulted_nonce, registered with permission_callback set to __return_true. This allows...

RAG-Targeted Adversarial Attack on LLM-Based Threat Detection and Mitigation Framework

The rapid expansion of the Internet of Things IoT is reshaping communication and operational practices across industries, but it also broadens the attack surface and increases susceptibility to security breaches. Artificial Intelligence has become a valuable solution in securing IoT networks, wit...

Large Language Models for Explainable Threat Intelligence

As cyber threats continue to grow in complexity, traditional security mechanisms struggle to keep up. Large language models LLMs offer significant potential in cybersecurity due to their advanced capabilities in text processing and generation. This paper explores the use of LLMs with...

EUVD-2025-38083

Insertion of Sensitive Information Into Sent Data vulnerability in Sovlix MeetingHub meetinghub allows Retrieve Embedded Sensitive Data.This issue affects MeetingHub: from n/a through = 1.23.9...

EUVD-2025-38127

Insertion of Sensitive Information Into Sent Data vulnerability in Vito Peleg Atarim atarim-visual-collaboration allows Retrieve Embedded Sensitive Data.This issue affects Atarim: from n/a through = 4.2...

CVE-2025-62039

Insertion of Sensitive Information Into Sent Data vulnerability in Ays Pro AI ChatBot with ChatGPT and Content Generator by AYS ays-chatgpt-assistant allows Retrieve Embedded Sensitive Data.This issue affects AI ChatBot with ChatGPT and Content Generator by AYS: from n/a through = 2.6.6...

Revive Adserver: Unrestricted setPerPage allows huge result sets / resource exhaustion / mass log retrieval

Description: The setPerPage query parameter controls pagination for the log viewer but is not validated or capped on the server. An attacker can supply an extremely large numeric value for example setPerPage=100000000000000000 and the application will attempt to honor that value when building the...

PT-2025-45306

Insertion of Sensitive Information Into Sent Data vulnerability in Ays Pro AI ChatBot with ChatGPT and Content Generator by AYS ays-chatgpt-assistant allows Retrieve Embedded Sensitive Data.This issue affects AI ChatBot with ChatGPT and Content Generator by AYS: from n/a through = 2.6.6...

PT-2025-45305

Insertion of Sensitive Information Into Sent Data vulnerability in Sovlix MeetingHub meetinghub allows Retrieve Embedded Sensitive Data.This issue affects MeetingHub: from n/a through = 1.23.9...

GO-2025-4000 Canonical LXD Path Traversal Vulnerability in Instance Log File Retrieval Function in github.com/canonical/lxd

Canonical LXD Path Traversal Vulnerability in Instance Log File Retrieval Function in github.com/canonical/lxd...