BerriAI litellm has Security Feature Bypass in BannedKeywords and AzureContentSafety Guardrails via call_type Mismatch on Async Endpoints

A security flaw has been discovered in BerriAI litellm up to 1.82.5. Affected is the function asyncprecallhook of the file enterprise/enterprisehooks/bannedkeywords.py of the component Completions Interface. The manipulation of the argument prompt results in incorrect authorization. The attack ma...

CVE-2026-96561

The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Stored Cross-Site Scripting in versions up to, and including, 3.8.0 This is due to a chain of missing input neutralization and output escaping across the /mwai-ui/v1/chats/submit REST endpoint, the...

EUVD-2026-90465

The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Stored Cross-Site Scripting in versions up to, and including, 3.8.0 This is due to a chain of missing input neutralization and output escaping across the /mwai-ui/v1/chats/submit REST endpoint, the...

CVE-2026-96561 AI Engine <= 3.8.0 - Unauthenticated Stored Cross-Site Scripting via 'model_' Parameter → PHP Error-Log Injection → Advisor Indirect Prompt Injection

The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Stored Cross-Site Scripting in versions up to, and including, 3.8.0 This is due to a chain of missing input neutralization and output escaping across the /mwai-ui/v1/chats/submit REST endpoint, the...

CVE-2026-96561 AI Engine <= 3.8.0 - Unauthenticated Stored Cross-Site Scripting via 'model_' Parameter → PHP Error-Log Injection → Advisor Indirect Prompt Injection

The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Stored Cross-Site Scripting in versions up to, and including, 3.8.0 This is due to a chain of missing input neutralization and output escaping across the /mwai-ui/v1/chats/submit REST endpoint, the...

CVE-2026-96561

The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin is vulnerable to Stored Cross-Site Scripting (XSS) in versions up to and including 3.8.0 . The vulnerability stems from a chain of missing input neutralization and output escaping starting at the /mwai-ui/v1/chats/submit REST en...

PT-2026-103667

The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Stored Cross-Site Scripting in versions up to, and including, 3.8.0 This is due to a chain of missing input neutralization and output escaping across the /mwai-ui/v1/chats/submit REST endpoint, the...

CVE-2026-96561: Improper Neutralization of Input During Web Page Generation

The AI Engine – The Chatbot, AI Framework & MCP for WordPress plugin for WordPress is vulnerable to Stored Cross-Site Scripting in versions up to, and including, 3.8.0 This is due to a chain of missing input neutralization and output escaping across the /mwai-ui/v1/chats/submit REST endpoint, the...

Evaluating and Improving the Robustness of Large Language Models to Input Sequence Variations

Large language models LLMs in production systems face prompt injections, trojans backdoors, and manipulation of automatic quality metrics. This thesis develops models, methods, and algorithms for evaluating and improving LLM robustness to adversarial input sequence variations. We propose Rstabf, ...

Rocky Linux 8 [CIQ] Security Update: firefox / firefox-debuginfo / firefox-debugsource Multiple Vulnerabilities (crlsa-2022_1705)

The Rocky Linux 8 host has packages installed that are affected by multiple vulnerabilities as referenced in the CIQ crlsa-20221705 advisory. Mozilla: Bypassing permission prompt in nested browsing contexts CVE-2022-29909 Mozilla: iframe Sandbox bypass CVE-2022-29911 Mozilla: Fullscreen...

AlmaLinux 9.2 [TuxCare] Security Update: git / git-all / git-core / git-core-doc / git-credential-libsecret / etc (ALMALINUX9.2:CLSA-2025:1761744708)

The AlmaLinux 9.2 host has packages installed that are affected by a vulnerability as referenced in the TuxCare ALMALINUX9.2:CLSA-2025:1761744708 advisory. - Git is a fast, scalable, distributed revision control system with an unusually rich command set that provides both high-level operations an...

Rocky Linux 8 [CIQ] Security Update: zsh / zsh-debuginfo / zsh-debugsource / zsh-html (crlsa-2022_2120)

The Rocky Linux 8 host has packages installed that are affected by a vulnerability as referenced in the CIQ crlsa-20222120 advisory. zsh: Prompt expansion vulnerability CVE-2021-45444 Tenable has extracted the preceding description block directly from the CIQ security advisory. Note that Nessus h...

CentOS Linux 7 [TuxCare] Security Update: emacs-git / emacs-git-el / git / git-all / git-bzr / git-cvs / etc (CENTOS7:CLSA-2026:1768310750)

The CentOS Linux 7 host has packages installed that are affected by a vulnerability as referenced in the TuxCare CENTOS7:CLSA-2026:1768310750 advisory. - Git is a fast, scalable, distributed revision control system with an unusually rich command set that provides both high-level operations and fu...

Rocky Linux 8 [CIQ] Security Update: thunderbird / thunderbird-debuginfo / thunderbird-debugsource Multiple Vulnerabilities (crlsa-2022_1730)

The Rocky Linux 8 host has packages installed that are affected by multiple vulnerabilities as referenced in the CIQ crlsa-20221730 advisory. Mozilla: Bypassing permission prompt in nested browsing contexts CVE-2022-29909 Mozilla: iframe Sandbox bypass CVE-2022-29911 Mozilla: Fullscreen...

Linux Distros Unpatched Vulnerability : CVE-2026-102938

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - virtualenv is a tool for creating isolated virtual python environments. Prior to 21.7.11, PyEnvCfg.write writes prompt values verbatim to the line-oriented...

PT-2026-104054

Name of the Vulnerable Software and Affected Versions Office-PowerPoint-MCP-Server versions prior to 2.0.8 Description A path traversal issue allows callers to read and write files outside the intended working directory by using absolute paths or ../ sequences. An attacker can use prompt injectio...

GHSA-9H9J-4VRJ-GF7G virtualenv writes prompt values into pyvenv.cfg without sanitizing line boundaries, allowing configuration injection

Summary pyvenv.cfg is a line-based format with no escape syntax. PyEnvCfg.write wrote values verbatim, while PyEnvCfg.readvalues parses the file with str.splitlines. A value containing a line boundary therefore became additional configuration lines, and because reading is last-wins, the injected...

virtualenv writes prompt values into pyvenv.cfg without sanitizing line boundaries, allowing configuration injection

Summary pyvenv.cfg is a line-based format with no escape syntax. PyEnvCfg.write wrote values verbatim, while PyEnvCfg.readvalues parses the file with str.splitlines. A value containing a line boundary therefore became additional configuration lines, and because reading is last-wins, the injected...

From A2A Attacks to Envelope-Layer Defense: Red-Teaming Evaluation of LLM Agents and a Three-Layer Isomorphic Attack-Defense Model

Agent interaction protocols such as ACP and A2A have moved LLM-based agents toward multi-agent collaboration, introducing new security threats. A task sent by a remote peer over A2A is treated as a legitimate request, providing a natural channel for indirect prompt injection. Existing agent...

Aletheia: Permission-Minimality Testing for Coding-Agent Rules

Repository instruction files guide coding agents, but also expose them to prompt injection. Malicious rules can request credential access or data transfer while the agent produces a correct patch. We present Aletheia, a framework for permission-minimality testing. Aletheia translates requested...