Security vulnerabilities, privacy incidents, safety concerns, and policy updates affecting LLMs and AI agents.
CVE-2026-25083 is a missing authorization vulnerability in GROWI (a collaboration platform) affecting version 7.4.5 and earlier. A logged-in user who knows the identifier of a shared AI assistant can view and modify other users' conversation threads and messages without permission, because the API endpoints don't properly verify whether the user should have access. This is rated as HIGH severity with a CVSS score (a 0-10 scale measuring vulnerability severity) of 8.7.
The Greenshift plugin for WordPress (used to create animations and page builder blocks) has a vulnerability where automated backup files are stored in a publicly accessible location, allowing attackers to read sensitive API keys (for OpenAI, Claude, Google Maps, Gemini, DeepSeek, and Cloudflare Turnstile) without needing to log in. This affects all versions up to 12.8.3.
OpenClaw versions before 2026.2.14 have a server-side request forgery vulnerability (SSRF, where an attacker tricks a server into making requests to unintended targets) in the Feishu extension that allows attackers to fetch remote URLs and access internal services through the sendMediaFeishu function and markdown image processing. Attackers can exploit this by manipulating tool calls or using prompt injection (tricking the AI by hiding instructions in its input) to trigger these requests and re-upload the responses as Feishu media.
OpenClaw's canvas tool contains a path traversal vulnerability (a security flaw that allows reading files outside intended directories) in its `a2ui_push` action. An authenticated attacker can supply any filesystem path to the `jsonlPath` parameter, and the gateway reads the file without validation and forwards its contents to connected nodes, potentially exposing sensitive files like credentials or SSH keys.
The BetterDocs plugin for WordPress (all versions up to 4.3.3) has a vulnerability that exposes sensitive information, allowing authenticated attackers with contributor-level access or higher to extract data including OpenAI API keys stored in the plugin settings through the scripts() function. This affects any WordPress site using the plugin where users have contributor-level permissions or above.
A WordPress plugin called 'Tag, Category, and Taxonomy Manager – AI Autotagger with OpenAI' has a security flaw (CWE-862, missing authorization) in versions up to 3.41.0 that allows contributors and higher-level users to add or remove taxonomy terms (tags and categories) on any post, even ones they don't own, due to missing permission checks. This vulnerability affects authenticated users who have contributor-level access or above.
LibreChat (a ChatGPT alternative with extra features) versions 0.8.0 and below have a security flaw where JSON parsing errors aren't properly handled, causing user input to appear in error messages. This can expose HTML or JavaScript code in responses, creating an XSS risk (cross-site scripting, where attackers inject malicious code that runs in users' browsers).
A WordPress plugin called AI Autotagger with OpenAI has a security flaw called time-based blind SQL injection (a technique where attackers sneak extra database commands into legitimate queries by exploiting how the software processes user input) in versions up to 3.40.1. Attackers with contributor-level access or higher can use this flaw to steal sensitive data from the database, slow down the website, or extract information through time-delay tricks.
A WordPress plugin called AI Autotagger with OpenAI has a security flaw in versions up to 3.40.1 where it fails to properly check if users have permission to perform certain actions. This authorization bypass (a failure to verify that someone is allowed to do something) allows authenticated attackers with basic subscriber-level access to merge or delete taxonomy terms (categories and tags used to organize content) that they shouldn't be able to modify.
The S2B AI Assistant WordPress plugin (a tool that adds AI chatbot features to websites) has a vulnerability in versions up to 1.7.8 where it fails to check what type of files users are uploading. This allows editors and higher-level users to upload malicious files that could potentially let attackers run commands on the website server (remote code execution, or RCE).
The WP Import – Ultimate CSV XML Importer plugin for WordPress has a security flaw in versions up to 7.33 where the showsetting() function is missing an authorization check (a verification that the person accessing it has permission). This allows authenticated attackers with Author-level access or higher to extract sensitive information, including OpenAI API keys (secret credentials used to access the OpenAI service) that are configured through the plugin's admin interface.
A WordPress plugin called Tag, Category, and Taxonomy Manager – AI Autotagger with OpenAI has a SQL injection vulnerability (a security flaw where attackers can insert harmful database commands into the plugin's code) in versions up to 3.40.0. Attackers with Editor-level access or higher can exploit the 'post_types' parameter to extract sensitive information from the website's database because the plugin doesn't properly clean up user input before using it in database queries.
The Better Find and Replace plugin for WordPress (versions up to 1.7.7) has a security flaw where a function called rtafar_ajax() doesn't properly check user permissions, allowing low-level authenticated users (Subscriber-level access) to trigger OpenAI API key usage and consume quota, potentially costing money. This happens because the code is missing a capability check (a permission verification system that controls what users can do).
A WordPress plugin called 'Ai Auto Tool Content Writing Assistant' (versions 2.0.7 to 2.2.6) has a security flaw where it doesn't properly check user permissions before allowing the save_post_data() function (a feature that stores post information) to run. This means even low-level users (Subscriber level and above) can create and publish posts they shouldn't be able to, allowing unauthorized modification of website content.
The Moodle OpenAI Chat Block plugin version 3.0.1 has an IDOR vulnerability (insecure direct object reference, where a user can access resources by directly requesting them without proper permission checks). An authenticated student can bypass validation of the blockId parameter in the plugin's API and impersonate another user's block, such as an administrator's block, allowing them to execute queries with that block's settings, expose sensitive information, and potentially misuse API resources.
Codex CLI (a coding tool from OpenAI that runs on your computer) versions 0.2.0 to 0.38.0 had a sandbox bug that allowed the AI model to trick the system into writing files and running commands outside the intended workspace folder. The sandbox (a restricted area meant to contain the tool's actions) wasn't properly checking where it should allow file access, which bypassed security boundaries, though network restrictions still worked.
Fix: Upgrade OpenClaw to version 2026.2.14 or later.
NVD/CVE DatabaseOpenAI fired an employee who used confidential company information to make trades on prediction markets (platforms like Polymarket where people bet money on real-world events). The employee's actions violated OpenAI's internal policy against using insider information for personal financial gain.
Anthropic accused three Chinese AI companies (DeepSeek, Moonshot AI, and MiniMax) of using distillation (a technique where one AI model learns from another by analyzing its outputs) to illegally extract capabilities from Claude by creating over 24,000 fake accounts and generating millions of interactions. This theft targeted Claude's most advanced features like reasoning, tool use, and coding, and raises security concerns because stolen models may lack safeguards against misuse like bioweapon development.
Fix: Anthropic stated it will 'continue to invest in defenses that make distillation attacks harder to execute and easier to identify,' and is calling on 'a coordinated response across the AI industry, cloud providers, and policymakers.' The company also argues that export controls on advanced AI chips to China would limit both direct model training and the scale of such distillation attacks.
TechCrunchOpenAI's monitoring tools flagged an 18-year-old user's chats on ChatGPT (a large language model chatbot) that described gun violence, leading to the account being banned in June 2025. The company debated whether to alert Canadian police but decided the chats didn't meet reporting criteria, though OpenAI later contacted authorities after the user allegedly killed eight people in a mass shooting in Canada.
Typebot, an open-source chatbot builder, has a vulnerability in versions before 3.13.2 where malicious chatbots can execute JavaScript (code that runs in a user's browser) to steal stored credentials like OpenAI API keys and passwords. The vulnerability exists because an API endpoint returns plaintext credentials without checking if the person requesting them actually owns them.
Fix: Update to Typebot version 3.13.2, which fixes the issue.
NVD/CVE DatabaseFix: Update to version 4.3.4 or later, as indicated by the WordPress plugin repository changeset reference showing the fix was applied in that version.
NVD/CVE DatabaseFix: A patch is available. According to the source, users should update to the version fixed in the GitHub commit referenced at https://github.com/TaxoPress/TaxoPress/commit/5eb2cee861ebd109152eea968aca0259c078c8b0.
NVD/CVE DatabaseFix: Update to Codex CLI 0.39.0 or later, which fixes the sandbox boundary validation. The patch now checks that the sandbox boundaries are based on where the user started the session, not on paths generated by the model. If using the Codex IDE extension, update immediately to version 0.4.12. Users on 0.38.0 or earlier should update via their package manager or reinstall the latest version.
NVD/CVE Database