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.
Documented production AI failures, mapped to PSF domains. Use these as case studies and failure-mode references.
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.
Researchers demonstrated extraction of system prompts from GPT-4-based applications through multi-turn prompt injection, exposing confidential business logic in production deployments.
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.
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.
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.
Vulnerabilities in AI/ML toolchains from the past 90 days. Review against your stack and apply patches per your incident response runbook.
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. Prior to version 1.21.0, there is an issue in onnx.load, the code checks for symlinks to prevent path traversal, but completely misses hardlinks because a hardlink looks exactly like a …
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. Prior to version 1.21.0, the ExternalDataInfo class in ONNX was using Python’s setattr() function to load metadata (like file paths or data lengths) directly from an ONNX model file. It…
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. Prior to version 1.21.0, a path traversal vulnerability via symlink allows to read arbitrary files outside model or user-provided directory. This issue has been patched in version 1.21.…
A flaw was found in Red Hat OpenShift AI (RHOAI) llama-stack-operator. This vulnerability allows unauthorized access to Llama Stack services deployed in other namespaces via direct network requests, because no NetworkPolicy restricts access to the llama-stack service endpoint. As…
llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the `ggml_nbytes` function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes `ggml_nbytes` to return a …
A vulnerability in MLflow's pyfunc extraction process allows for arbitrary file writes due to improper handling of tar archive entries. Specifically, the use of `tarfile.extractall` without path validation enables crafted tar.gz files containing `..` or absolute paths to escape t…
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. In versions up to and including 1.20.1, a security control bypass exists in onnx.hub.load() due to improper logic in the repository trust verification mechanism. While the function is d…
A command injection vulnerability exists in mlflow/mlflow versions before v3.7.0, specifically in the `mlflow/sagemaker/__init__.py` file at lines 161-167. The vulnerability arises from the direct interpolation of user-supplied container image names into shell commands without pr…
llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the…
Craft is a content management system (CMS). The ElementSearchController::actionSearch() endpoint is missing the unset() protection that was added to ElementIndexesController in CVE-2026-25495. The exact same SQL injection vulnerability (including criteria[orderBy], the original a…
Langchain Helm Charts are Helm charts for deploying Langchain applications on Kubernetes. Prior to langchain-ai/helm version 0.12.71, a URL parameter injection vulnerability existed in LangSmith Studio that could allow unauthorized access to user accounts through stolen authentic…
A vulnerability in NLTK versions up to and including 3.9.2 allows arbitrary file read via path traversal in multiple CorpusReader classes, including WordListCorpusReader, TaggedCorpusReader, and BracketParseCorpusReader. These classes fail to properly sanitize or validate file pa…
Gradio is an open-source Python package designed for quick prototyping. Prior to version 6.6.0, the _redirect_to_target() function in Gradio's OAuth flow accepts an unvalidated _target_url query parameter, allowing redirection to arbitrary external URLs. This affects the /logout …
Gradio is an open-source Python package designed for quick prototyping. Starting in version 4.16.0 and prior to version 6.6.0, Gradio applications running outside of Hugging Face Spaces automatically enable "mocked" OAuth routes when OAuth components (e.g. `gr.LoginButton`) are u…
Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.8.0, the CSV Agent node in Langflow hardcodes `allow_dangerous_code=True`, which automatically exposes LangChain’s Python REPL tool (`python_repl_ast`). As a result, an attacker can …
LangChain is a framework for building LLM-powered applications. Prior to version 1.1.8, a redirect-based Server-Side Request Forgery (SSRF) bypass exists in `RecursiveUrlLoader` in `@langchain/community`. The loader validates the initial URL but allows the underlying fetch to fol…
MLflow Use of Default Password Authentication Bypass Vulnerability. This vulnerability allows remote attackers to bypass authentication on affected installations of MLflow. Authentication is not required to exploit this vulnerability. The specific flaw exists within the basic_au…
MLflow Tracking Server Artifact Handler Directory Traversal Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of MLflow Tracking Server. Authentication is not required to exploit this vulnerability.…
strongMan is a management interface for strongSwan, an OpenSource IPsec-based VPN. When storing credentials in the database (private keys, EAP secrets), strongMan encrypts the corresponding database fields. So far it used AES in CTR mode with a global database key. Together with …
Milvus is an open-source vector database built for generative AI applications. Prior to 2.5.27 and 2.6.10, Milvus exposes TCP port 9091 by default, which enables authentication bypasses. The /expr debug endpoint uses a weak, predictable default authentication token derived from e…
newbee-mall stores and verifies user passwords using an unsalted MD5 hashing algorithm. The implementation does not incorporate per-user salts or computational cost controls, enabling attackers who obtain password hashes through database exposure, backup leakage, or other comprom…
LangChain is a framework for building LLM-powered applications. Prior to 1.1.14, the RecursiveUrlLoader class in @langchain/community is a web crawler that recursively follows links from a starting URL. Its preventOutside option (enabled by default) is intended to restrict crawli…
LangChain is a framework for building agents and LLM-powered applications. Prior to 1.2.11, the ChatOpenAI.get_num_tokens_from_messages() method fetches arbitrary image_url values without validation when computing token counts for vision-enabled models. This allows attackers to t…
A flaw has been found in ggml-org llama.cpp up to 55abc39. Impacted is the function llama_grammar_advance_stack of the file llama.cpp/src/llama-grammar.cpp of the component GBNF Grammar Handler. This manipulation causes stack-based buffer overflow. The attack needs to be launched…
Qdrant is a vector similarity search engine and vector database. From 1.9.3 to before 1.16.0, it is possible to append to arbitrary files via /logger endpoint using an attacker-controlled on_disk.log_file path. Minimal privileges are required (read-only access). This vulnerabilit…
In mlflow version 2.20.3, the temporary directory used for creating Python virtual environments is assigned insecure world-writable permissions (0o777). This vulnerability allows an attacker with write access to the `/tmp` directory to exploit a race condition and overwrite `.py`…
Llama Stack (aka llama-stack) before 0.4.0rc3 does not censor the pgvector password in the initialization log.
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.