What changed in AI security, Jun 8 to Jun 14, 2026
Jun 8 to Jun 14, 2026 (ISO week 2026-W24). Weeks run Monday to Sunday in UTC.
170 records published, +5 on the previous week: 30 vulnerabilities (+3), 0 incidents (no change), 12 research items (+4), 127 news items (no change), 1 policy item (-2).
Critical and high advisories
Vulnerability records rated critical or high, newest first.- High
CVE-2026-50287: AgenticMail gives AI agents real email addresses and phone numbers. Prior to version 0.9.27, @agenticmail/mcp exposes a…
CVE-2026-50287NVD/CVE Database - High
CVE-2026-8828: A lack of authorization validation in version 1.0.0 or later of the ChromaDB Rust project allows any authenticated…
CVE-2026-8828NVD/CVE Database - Critical
CVE-2026-45833: A code injection vulnerability in version 0.4.17 or later of the ChromaDB Python project allows an authenticated…
CVE-2026-45833NVD/CVE Database - High
CVE-2026-45832: All V1 collection-level endpoints in ChromaDB's Python project pass None for the tenant and database to the…
CVE-2026-45832NVD/CVE Database - High
CVE-2026-45831: The SimpleRBACAuthorizationProvider authorization provider in versions 0.5.0 or later of the ChromaDB Python project…
CVE-2026-45831NVD/CVE Database - High
CVE-2026-45830: A lack of authorization validation in version 0.4.17 or later of the ChromaDB Python project allows any authenticated…
CVE-2026-45830NVD/CVE Database - High
CVE-2026-7787: IBM Langflow OSS 1.0.0 through 1.9.1 could allow an authenticated user to read or modify sensitive information by…
CVE-2026-7787NVD/CVE Database - High
CVE-2026-11816: Keras versions prior to 3.14.0 are vulnerable to a path traversal issue in the archive extraction utilities located in…
CVE-2026-11816NVD/CVE Database - High
CVE-2026-5497: vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded…
CVE-2026-5497NVD/CVE Database - High
GHSA-j9rx-rppg-6hh4: Anyquery has Path Traversal through `clear_plugin_cache`, Allowing Arbitrary Directory Deletion
CVE-2026-47253GitHub Advisory Database - High
CVE-2026-46517: LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior…
CVE-2026-46517NVD/CVE Database - High
CVE-2026-45482: Improper limitation of a pathname to a restricted directory ('path traversal') in GitHub Copilot and Visual Studio Code…
CVE-2026-45482NVD/CVE Database - High
CVE-2026-11393 - Code Injection via Improper Triple-Quote Escaping in AgentCore CLI Bedrock Agent Import
AWS Security Bulletins - High
CVE-2026-46480: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to version 3.1.2…
CVE-2026-46480NVD/CVE Database - High
CVE-2026-46479: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to version 3.1.2…
CVE-2026-46479NVD/CVE Database - High
CVE-2026-46478: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to version 3.1.2…
CVE-2026-46478NVD/CVE Database - High
CVE-2026-46477: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to version 3.1.2…
CVE-2026-46477NVD/CVE Database - High
CVE-2026-46476: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to version 3.1.2…
CVE-2026-46476NVD/CVE Database - High
CVE-2026-46475: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to version 3.1.2…
CVE-2026-46475NVD/CVE Database - High
CVE-2026-46444: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to version 3.1.2, all…
CVE-2026-46444NVD/CVE Database - High
CVE-2026-46443: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to version 3.1.2, when…
CVE-2026-46443NVD/CVE Database - Critical
CVE-2026-46442: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to version 3.1.2, POST…
CVE-2026-46442NVD/CVE Database - High
CVE-2026-46440: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to version 3.1.2, the…
CVE-2026-46440NVD/CVE Database
Exploitation signals
Vulnerabilities published in the week that are listed in the CISA Known Exploited Vulnerabilities catalog or have an EPSS score of 10% or more.No vulnerability published in this week is listed as exploited or has an EPSS score of 10% or more.
Packages that began delegating to a language model
Exposure Registry packages whose first release declaring an LLM SDK, agent framework or MCP dependency was published in the week.| Package | Ecosystem | LLM SDKs | Release | Released |
|---|---|---|---|---|
| gliner-py | PyPI | Hugging Face Hub / Transformers | 0.2.27 |
Topics that moved
Largest increases over the mean of the 4 previous weeks, for topics with at least 3 records in the week.| Topic | Records | Weekly mean, previous 4 | Difference |
|---|---|---|---|
| Prompt injection and jailbreaks | 3 | 1.8 | +1.3 |
| Coding assistants | 4 | 3.3 | +0.8 |
Research
Peer-reviewed first, then newest. Showing 8 of 12.Rethinking ransomware defense in the age of generative AI
Peer-reviewedElsevier Security JournalsA Survey of Neural Network Robustness Assessment in Image Recognition
Peer-reviewedACM Digital Library (TOPS, DTRAP, CSUR)Enhanced privacy-preserving neural networks with fully homomorphic encryption: Optimized search and training
Peer-reviewedElsevier Security JournalsWatermarking for Model Ownership Verification:Invisible at Deployment, Activated by Updates
Peer-reviewedACM Digital Library (TOPS, DTRAP, CSUR)With Power comes Responsibility: Attack Synthesis for Industrial Control Systems using Large Language Models
Peer-reviewedACM Digital Library (TOPS, DTRAP, CSUR)Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector
Peer-reviewedIEEE Xplore (Security & AI Journals)Dual Attention Guided Defense Against Malicious Edits
Peer-reviewedIEEE Xplore (Security & AI Journals)FIT-Print: Toward False-Claim-Resistant Model Ownership Verification via Targeted Fingerprint
Peer-reviewedIEEE Xplore (Security & AI Journals)
Policy and regulation
Newest first.Generated from the AI Sec Watch database at . Every item links to its record.