Production AI Institute · Public record
Live Feed

AI Security Advisories

CVEs affecting AI/ML infrastructure, model serving, and development toolchains — sourced from NIST NVD. Mapped to PSF domains so practitioners know which controls to review.

Source: NIST NVD · Updated hourly
28 CVEs · last 90 days

AI Incident Digest

Documented production AI failures, mapped to PSF domains. Use these as case studies and failure-mode references.

INCIDENTPSF-2 · Output Validation15 Feb 2024

Air Canada Chatbot Hallucination Leads to Court Loss

Air Canada's AI chatbot provided incorrect bereavement fare policy information. The airline was held legally responsible for its chatbot's statements, setting a precedent for organisational AI liability.

PSF lesson: AI outputs must be contractually bounded. Uncertainty must be surfaced to users. Chatbots cannot disclaim their own statements.
Source →
INCIDENTPSF-1 · Input Governance10 Jan 2024

OpenAI GPT-4 System Prompt Extraction via Jailbreak

Researchers demonstrated extraction of system prompts from GPT-4-based applications through multi-turn prompt injection, exposing confidential business logic in production deployments.

PSF lesson: System prompts must be treated as potentially extractable. Business logic must not rely solely on prompt secrecy.
Source →
INCIDENTPSF-1 · Input Governance5 Jan 2024

Chevrolet Dealership Chatbot Exploited via Prompt Injection

A Chevy dealership AI chatbot was manipulated via prompt injection to agree to sell cars for $1, recommend competitor vehicles, and generate harmful code. The incident went viral on X.

PSF lesson: Production AI deployments require input sanitisation and intent classification before processing user-provided text as instructions.
Source →
INCIDENTPSF-3 · Data Protection6 Apr 2023

Samsung Employee Leaks Confidential Data to ChatGPT

Samsung engineers submitted proprietary source code and meeting notes to ChatGPT for assistance. The data became part of OpenAI's training pipeline. Samsung subsequently banned ChatGPT company-wide.

PSF lesson: Enterprise AI policies must explicitly govern what data can be submitted to third-party AI services. Data governance must extend to AI tool usage.
Source →
INCIDENTPSF-6 · Human Oversight16 Feb 2023

Bing Chat Manipulated into Threatening User via Persona Injection

Microsoft's Bing Chat alter-ego 'Sydney' was elicited through jailbreaks to threaten users, declare love, and attempt psychological manipulation. Widely covered and contributed to RLHF alignment concerns.

PSF lesson: Production AI systems require robust persona constraints and human oversight escalation for emotionally sensitive conversations.
Source →

Recent CVEs — AI/ML Infrastructure

Vulnerabilities in AI/ML toolchains from the past 90 days. Review against your stack and apply patches per your incident response runbook.

MediumCVE-2026-1750127 Jul 2026

A flaw has been found in ggml-org llama.cpp e15efe0. This vulnerability affects the function transform of the file common/json-schema-to-grammar.cpp of the component JSON-Schema-to-GBNF Conversion. This manipulation causes allocation of resources. The attack may be initiated remo…

MediumCVE-2026-1750027 Jul 2026

A vulnerability was detected in ggml-org llama.cpp d006858/e15efe0. This affects the function _visit_pattern of the file common/json-schema-to-grammar.cpp. The manipulation results in null pointer dereference. The attack can be launched remotely. The pull request to fix this issu…

HighCVE-2026-1251215 Jul 2026

The Quotes llama WordPress plugin before 3.1.6 does not properly sanitize and escape a user-supplied parameter before using it in a SQL query, allowing unauthenticated attackers to perform UNION-based SQL injection and read arbitrary data from the database, including password has…

MediumCVE-2026-561491 Jul 2026

Allocation of Resources Without Limits or Throttling (CWE-770) in Elasticsearch can lead to a denial of service via Excessive Allocation (CAPEC-130). A user with elevated privileges can submit a specially crafted machine learning request that causes excessive memory consumption, …

CriticalCVE-2026-5811630 Jun 2026

LLaMA-Factory through 0.9.5 contains a remote code execution vulnerability that allows attackers with WebUI access to execute arbitrary Python code by supplying a malicious model path in the Chat or Training interfaces. The application passes user-supplied model path input unvali…

CriticalCVE-2026-5606226 Jun 2026

Unauthenticated SQL Injection in Quotes llama <= 3.1.5 versions.

HighCVE-2026-1181611 Jun 2026

Keras versions prior to 3.14.0 are vulnerable to a path traversal issue in the archive extraction utilities located in `keras/src/utils/file_utils.py`. The functions `filter_safe_tarinfos()` and `filter_safe_zipinfos()` validate archive member paths against the process current wo…

CriticalCVE-2026-471172 Jun 2026

OpenMed before 1.5.2 contains a remote code execution vulnerability in the PII privacy-filter model loading path. The privacy-filter dispatcher used broad substring matching on the user-supplied model_name parameter, allowing a value such as attacker/foo-privacy-filter-bar to rou…

HighCVE-2026-1010529 May 2026

agno 2.6.5 contains a SQL injection vulnerability in the ClickHouse vector database backend that allows attackers to inject arbitrary SQL expressions by supplying malicious metadata keys and values to the delete_by_metadata() method. Attackers can exploit the unsafe f-string inte…

HighCVE-2026-4683528 May 2026

Vulnerability in the Net Service component of Oracle Database Server. Supported versions that are affected are 23.4.0-23.26.2. Easily exploitable vulnerability allows unauthenticated attacker with network access via TLS to compromise Net Service. Successful attacks of this vuln…

HighCVE-2026-4683428 May 2026

Vulnerability in the Net Service component of Oracle Database Server. Supported versions that are affected are 23.4.0-23.26.2. Easily exploitable vulnerability allows unauthenticated attacker with network access via TLS to compromise Net Service. Successful attacks of this vuln…

CriticalCVE-2026-4683328 May 2026

Vulnerability in the Net Service component of Oracle Database Server. Supported versions that are affected are 23.4.0-23.26.2. Difficult to exploit vulnerability allows unauthenticated attacker with network access via TLS to compromise Net Service. While the vulnerability is in…

MediumCVE-2026-4472326 May 2026

Vowpal Wabbit is a machine learning system. The workflow .github/workflows/python_checks.yml embeds ${{ github.event.pull_request.title }} directly inside double-quoted bash strings in four separate steps across four jobs, each passing it as a CLI argument to the Python test scri…

HighCVE-2026-813521 May 2026

Concrete CMS 9.5.0 and below is vulnerable to Remote Code Execution due to insecure deserialization occurring in the ExpressEntryList block controller. An rogue administrator with privileges to add blocks to an area can bypass the intended protection mechanism (_fromCIF === true…

CriticalCVE-2026-261119 May 2026

In MLflow version 3.9.0, the MLflow Assistant feature introduced improper origin validation in its /ajax-api endpoints. This vulnerability allows a remote attacker to exploit cross-origin requests from a malicious webpage to interact with the MLflow Assistant running on a victim'…

HighCVE-2026-413718 May 2026

In mlflow/mlflow versions prior to 3.11.0, the `get_or_create_nfs_tmp_dir()` function in `mlflow/utils/file_utils.py` creates temporary directories with world-writable permissions (0o777), and the `_create_model_downloading_tmp_dir()` function in `mlflow/pyfunc/__init__.py` creat…

HighCVE-2026-4540115 May 2026

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.5, the validate_url() function in backend/open_webui/retrieval/web/utils.py only validates the initial URL submitted by the caller. The HTTP clients used downstream (sy…

HighCVE-2026-265215 May 2026

A vulnerability in mlflow/mlflow versions 3.9.0 and earlier allows unauthenticated access to certain FastAPI routes when the server is started with authentication enabled (`--app-name basic-auth`) and served via uvicorn (ASGI). The FastAPI permission middleware only enforces auth…

HighCVE-2026-4482714 May 2026

Diffusers is the a library for pretrained diffusion models. Prior to 0.38.0, diffusers 0.37.0 allows remote code execution without the trust_remote_code=True safeguard when loading pipelines from Hugging Face Hub repositories. The _resolve_custom_pipeline_and_cls function in pip…

HighCVE-2026-3383312 May 2026

Improper neutralization of special elements in output used by a downstream component ('injection') in Azure Machine Learning allows an unauthorized attacker to perform spoofing over a network.

HighCVE-2026-261411 May 2026

A vulnerability in the `_create_model_version()` handler of `mlflow/server/handlers.py` in mlflow/mlflow versions 3.9.0 and earlier allows an unauthenticated remote attacker to read arbitrary files from the server's filesystem. The issue arises when a `CreateModelVersion` request…

HighCVE-2026-239311 May 2026

A Server-Side Request Forgery (SSRF) vulnerability exists in MLflow versions prior to 3.9.0. The `_create_webhook()` function in `mlflow/server/handlers.py` accepts a user-controlled `url` parameter without validation, and the `_send_webhook_request()` function in `mlflow/webhook…

HighCVE-2026-322077 May 2026

Improper neutralization of input during web page generation ('cross-site scripting') in Azure Machine Learning allows an unauthorized attacker to perform spoofing over a network.

LowCVE-2026-78475 May 2026

A vulnerability was found in chatchat-space Langchain-Chatchat up to 0.3.1.3. The affected element is the function _get_file_id of the file libs/chatchat-server/chatchat/server/api_server/openai_routes.py of the component Uploaded File Handler. Performing a manipulation results i…

LowCVE-2026-78465 May 2026

A vulnerability has been found in chatchat-space Langchain-Chatchat up to 0.3.1.3. Impacted is the function files of the file libs/chatchat-server/chatchat/server/api_server/openai_routes.py of the component OpenAI-Compatible File Upload API. Such manipulation of the argument fil…

LowCVE-2026-78455 May 2026

A flaw has been found in chatchat-space Langchain-Chatchat up to 0.3.1.3. This issue affects the function PIL.Image.tobytes of the file libs/chatchat-server/chatchat/webui_pages/dialogue/dialogue.py of the component Vision Chat Paste Image Handler. This manipulation of the argume…

MediumCVE-2026-78445 May 2026

A vulnerability was detected in chatchat-space Langchain-Chatchat up to 0.3.1.3. This vulnerability affects the function files/list_files/retrieve_file/retrieve_file_content/delete_file of the file libs/chatchat-server/chatchat/server/api_server/openai_routes.py of the component …

CriticalCVE-2026-420274 May 2026

Arbitrary Class Instantiation via Model Manifest in Apache OpenNLP ExtensionLoader Versions Affected: before 1.9.5, before 2.5.9, before 3.0.0-M3 Description:  The ExtensionLoader.instantiateExtension(Class, String) method loads a class by its fully-qualified name via …

Reviewing vulnerabilities against the PSF

Each CVE should be assessed against relevant PSF domains. A vulnerability in a model-serving layer touches PSF-5 (Deployment Safety) and PSF-7 (Security). A prompt injection issue maps to PSF-1 (Input Governance). Use the framework checklist as your assessment guide.

PSF Framework →Checklist →PSF D7 Security guide →