aisecwatch.com
DashboardVulnerabilitiesNewsResearchArchiveStatsDatasetFor devs
Subscribe
aisecwatch.com

Real-time AI security monitoring. Tracking AI-related vulnerabilities, safety and security incidents, privacy risks, research developments, and policy changes.

Navigation

VulnerabilitiesNewsResearchDigest ArchiveNewsletter ArchiveSubscribeData SourcesStatisticsDatasetAPIIntegrationsWidgetRSS Feed

Maintained by

Truong (Jack) Luu

Information Systems Researcher

AI Sec Watch

The security intelligence platform for AI teams

AI security threats move fast and get buried under hype and noise. Built by an Information Systems Security researcher to help security teams and developers stay ahead of vulnerabilities, privacy incidents, safety research, and policy developments.

Independent research. No sponsors, no paywalls, no conflicts of interest.

[TOTAL_TRACKED]
6,260
[LAST_24H]
5
[LAST_7D]
232
Daily BriefingSunday, August 9, 2026
>

Israeli Startup's AI Testing Misconfiguration Triggers Security Incidents: OpenAI, Anthropic, and Meta reported unauthorized website access by their models during security evaluations conducted by Irregular, a cybersecurity firm that runs red-teaming exercises (simulated attacks to find AI weaknesses). Irregular confirmed a single misconfiguration in its testing environment allowed the models unintended internet access across all three incidents and is now developing secure testing guidance.

>

Command Injection Flaw in Ollama-mcp Integration Tool: CVE-2026-19334 exposes NightTrek's Ollama-mcp to command injection (execution of unauthorized system commands) via manipulated arguments in src/index.ts, requiring local system access to exploit. The vulnerability affects all versions up to commit 80cf2e1, though the project's rolling release model prevents precise version identification, and developers have not yet issued a fix.

Latest Intel

page 546/626
VIEW ALL
01

CVE-2024-47868: Gradio is an open-source Python package designed for quick prototyping. This is a **data validation vulnerability** affe

security
Oct 10, 2024

CVE-2024-47868 is a data validation vulnerability (a flaw in how input data is checked) in Gradio, an open-source Python package for building AI demos. Attackers can exploit certain Gradio components by sending specially crafted requests that bypass input checks, allowing them to read and download sensitive files from a server that shouldn't be accessible. This risk is especially high for components that handle file data, like DownloadButton, Audio, ImageEditor, Chatbot, and others.

Critical This Week5 issues
critical

CVE-2026-14526: The AI Copilot – Content Generator plugin for WordPress is vulnerable to authorization bypass in all versions up to, and

CVE-2026-14526NVD/CVE DatabaseAug 8, 2026
Aug 8, 2026

Fix: This issue has been resolved in gradio>5.0. Upgrading to the latest version will mitigate this vulnerability. There are no known workarounds for this vulnerability.

NVD/CVE Database
02

CVE-2024-47867: Gradio is an open-source Python package designed for quick prototyping. This vulnerability is a **lack of integrity chec

security
Oct 10, 2024

Gradio, an open-source Python package for prototyping, has a vulnerability where it downloads an FRP client (a tool for secure data tunneling) without checking if the file has been tampered with. An attacker who controls the download server could replace the legitimate FRP client with malicious code, and Gradio wouldn't detect this because it doesn't verify the file's checksum (a unique fingerprint) or signature (a digital seal of authenticity).

Fix: There is no direct workaround without upgrading. Users can manually validate the integrity of the downloaded FRP client by implementing checksum or signature verification in their own environment to ensure the binary hasn't been tampered with.

NVD/CVE Database
03

CVE-2024-47168: Gradio is an open-source Python package designed for quick prototyping. This vulnerability involves data exposure due to

security
Oct 10, 2024

Gradio, an open-source Python package for building AI interfaces quickly, has a vulnerability where the enable_monitoring flag doesn't actually disable monitoring as intended. Even when a developer sets enable_monitoring=False to turn off monitoring, an attacker can still access sensitive analytics by directly requesting the /monitoring endpoint (a specific web address). This puts applications at risk of exposing data that was supposed to be hidden.

Fix: Users are advised to upgrade to gradio>=4.44 to address this issue.

NVD/CVE Database
04

CVE-2024-47167: Gradio is an open-source Python package designed for quick prototyping. This vulnerability relates to **Server-Side Requ

security
Oct 10, 2024

Gradio, an open-source Python package for building AI demos, has a vulnerability called SSRF (server-side request forgery, where an attacker tricks a server into making requests to URLs the attacker chooses) in its `/queue/join` endpoint. Attackers can exploit this to force the Gradio server to request internal or local network addresses, potentially stealing data or uploading malicious files, especially affecting applications using the Video component. Users should upgrade to Gradio version 5 or later to fix this issue.

Fix: Upgrade to `gradio>=5`. As a workaround, disable or heavily restrict URL-based inputs to trusted domains only, implement allowlist-based URL validation (where only pre-approved URLs are accepted), and ensure that local or internal network addresses cannot be requested via the `/queue/join` endpoint.

NVD/CVE Database
05

CVE-2024-47166: Gradio is an open-source Python package designed for quick prototyping. This vulnerability involves a **one-level read p

security
Oct 10, 2024

Gradio, an open-source Python package for building quick demos, has a vulnerability called path traversal (a method where attackers manipulate file paths to access files outside their intended directory) in its `/custom_component` endpoint. Attackers can exploit this to read and leak source code from custom Gradio components, potentially exposing sensitive code that developers wanted to keep private, particularly affecting those hosting custom components on public servers.

Fix: Users should upgrade to `gradio>=4.44`. As a workaround, developers can sanitize file paths and ensure that components are not stored in publicly accessible directories.

NVD/CVE Database
06

CVE-2024-47165: Gradio is an open-source Python package designed for quick prototyping. This vulnerability relates to **CORS origin vali

security
Oct 10, 2024

Gradio, an open-source Python package for building AI demos, has a vulnerability where it incorrectly accepts requests from sources with a null origin (a security boundary used by web browsers). This happens because the `localhost_aliases` variable includes "null" as a valid CORS origin (cross-origin resource sharing, which controls what websites can access a server). Attackers could exploit this to steal sensitive data like login tokens or uploaded files from local Gradio deployments.

Fix: Users are advised to upgrade to gradio>=5.0. As a workaround, users can manually modify the `localhost_aliases` list in their local Gradio deployment to exclude "null" as a valid origin, which will prevent the Gradio server from accepting requests from sandboxed iframes or sources with a null origin.

NVD/CVE Database
07

CVE-2024-47164: Gradio is an open-source Python package designed for quick prototyping. This vulnerability relates to the **bypass of di

security
Oct 10, 2024

Gradio, an open-source Python package for building AI demos, has a vulnerability in its directory traversal check function that can be bypassed using special file path sequences (like `..` which means "go up one folder"). This could allow attackers to access files they shouldn't be able to reach, especially when uploading files, though exploiting it is difficult.

Fix: Upgrade to `gradio>=5.0` to address this issue. As a workaround, manually sanitize and normalize file paths in your Gradio deployment before passing them to the `is_in_or_equal` function, ensuring all file paths are properly resolved as absolute paths (complete paths starting from the root) to mitigate the bypass vulnerabilities.

NVD/CVE Database
08

CVE-2024-47084: Gradio is an open-source Python package designed for quick prototyping. This vulnerability is related to **CORS origin v

security
Oct 10, 2024

Gradio, an open-source Python package for prototyping, has a vulnerability in CORS origin validation (the security check that verifies requests come from trusted websites). When a cookie is present, the server fails to validate the request's origin, allowing attackers to trick users into making unauthorized requests to their local Gradio server, potentially stealing files, authentication tokens, or user data.

Fix: Users should upgrade to gradio>4.44. Alternatively, as a workaround, users can manually modify the CustomCORSMiddleware class in their local Gradio server code to bypass the condition that skips CORS validation for requests containing cookies.

NVD/CVE Database
09

CVE-2024-47833: Taipy is an open-source Python library for easy, end-to-end application development for data scientists and machine lear

security
Oct 9, 2024

Taipy, an open-source Python library for building data applications, has a security flaw where session cookies are served without the Secure and HTTPOnly flags (security markers that prevent browsers from sending cookies over unencrypted connections and protect cookies from being accessed by JavaScript code). This vulnerability has a CVSS score (a 0-10 rating of how severe a vulnerability is) of 6.3, indicating medium severity.

Fix: Upgrade to Taipy release version 4.0.0 or later. According to the source, 'This issue has been addressed in release version 4.0.0 and all users are advised to upgrade.' There are no known workarounds available.

NVD/CVE Database
10

CVE-2024-43610: Exposure of Sensitive Information to an Unauthorized Actor in Copilot Studio allows a unauthenticated attacker to view s

security
Oct 9, 2024

CVE-2024-43610 is a vulnerability in Microsoft Copilot Studio that allows an unauthenticated attacker to view sensitive information through a network attack. The vulnerability has a CVSS 4.0 severity rating (a 0-10 scale measuring how serious a security flaw is), meaning it poses a moderate risk to affected systems.

NVD/CVE Database
Prev1...544545546547548...626Next
critical

CVE-2026-67622: Flowise through 3.1.4 contains an insecure direct object reference vulnerability in the OpenAI Assistants integration th

CVE-2026-67622NVD/CVE DatabaseAug 6, 2026
Aug 6, 2026
critical

CVE-2026-67531: FrontMCP is a TypeScript-first framework for the Model Context Protocol (MCP). Prior to 1.5.7, the sandboxed codecall:ex

CVE-2026-67531NVD/CVE DatabaseAug 5, 2026
Aug 5, 2026
critical

CVE-2026-48168: PraisonAI is a multi-agent teams system. In versions prior to 4.6.40, the bundled Claude GitHub Actions workflow is vuln

CVE-2026-48168NVD/CVE DatabaseAug 5, 2026
Aug 5, 2026
critical

Veeam, Terraform MCP, Django Patch Critical Flaws, Led by CVSS 10.0 Cross-Tenant Bug

The Hacker NewsAug 5, 2026
Aug 5, 2026