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.
SitemapLoader.parse_sitemap in langchain_community/document_loaders/sitemap.py applies the documented restrict_to_same_domain control only to leaf url entries. The loop over url elements filters cross-domain locations, but the loop over nested sitemap elements passes the child lo…
MLflow is an open source AI engineering platform for agents, large language models, and machine learning models. Prior to 3.15.0, the unauthenticated POST /api/2.0/mlflow/webhooks/{id}/test endpoint calls _validate_webhook_url() in mlflow/utils/validation.py only for the original…
Hugging Face Transformers fails to validate shard filenames in checkpoint index files, allowing attackers to read arbitrary files outside the model directory. Attackers can supply malicious index files with parent-directory references or absolute paths that are joined without val…
Hugging Face Accelerate through 1.14.0 contains a path traversal vulnerability in load_checkpoint_in_model and load_checkpoint_and_dispatch functions that fail to sanitize weight_map entries from sharded checkpoint indexes. Attackers can supply relative paths with ../ sequences o…
Hugging Face peft's LoRA-GA and CorDA initialization modules (src/peft/tuners/lora/corda.py lines ~102 and ~163, and src/peft/tuners/lora/loraga.py line ~101) call torch.load on config-specified cache/covariance files without weights_only=True, bypassing peft's own safe-loading w…
MLflow's AI Gateway accepts an auth_config.api_base value when creating a gateway secret (mlflow/server/handlers.py, _create_gateway_secret) with no validation of scheme, host, or IP range; the value is stored verbatim. The gateway proxy endpoint (mlflow/server/gateway_api.py, ra…
NVIDIA Triton Inference Server for Linux contains a vulnerability where a user could cause files outside the model repository to be read, written to, or modified by providing a path in the model name to the Triton MLflow plugin. A successful exploit of this vulnerability might le…
A vulnerability in huggingface/transformers versions <=5.8.0.dev0 allows an attacker to perform arbitrary file writes via path traversal. The issue resides in the `save_pretrained()` methods of `PreTrainedTokenizerBase` and `ProcessorMixin`, where keys from the `chat_template` di…
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 uncontrolled recursion. The attack may be initiated remot…
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…
Uncontrolled Resource Consumption (CWE-400) in Kibana can lead to denial of service via Excessive Allocation (CAPEC-130). A low-privileged authenticated user can send a specially crafted request to a Kibana machine learning feature, causing the server to exhaust available memory …
Incorrect Authorization (CWE-863) in Kibana can lead to integrity compromise of Machine Learning audit and notification records via Accessing Functionality Not Properly Constrained by ACLs (CAPEC-1). A vulnerability exists in Kibana's Machine Learning functionality where a Machi…
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…
PraisonAI before 4.6.78 fails to validate the caller-controlled dimension argument in the PGVector and Cassandra knowledge-store create_collection() backends. Although schema, keyspace, and collection-name identifiers are validated, the dimension value (declared as int but not en…
LangChain4j is a Java library for building LLM-powered applications on the JVM. Prior to 1.2.1-beta8, 1.5.1-beta11, 1.11.8-beta19, and 1.16.3-beta26, the MariaDB and pgvector embedding stores build metadata-filter SQL by string-concatenating filter keys, and in MariaDB string va…
Dify before 1.16.0-rc1 contains a SQL injection vulnerability in the MyScale vector store backend that allows attackers to execute arbitrary SQL by supplying unsanitized search parameters to the search_by_full_text method without escaping or parameterization. Attackers can inject…
ChatterBot is a machine learning, conversational dialog engine for creating chat bots. Prior to 1.2.14, UbuntuCorpusTrainer.extract() uses a predictable home-rooted output directory (~/ubuntu_data/ubuntu_dialogs) with a check-then-create pattern followed by tar.extractall(path=se…
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.9.0 before 1.22.0, onnx.version_converter.convert_version() can dereference a null pointer in Upsample_6_7::adapt_upsample_6_7() in onnx/version_converter/adapters/upsample_6_7.h…
A vulnerability was determined in langchain-ai langgraph up to 1.2.4. The affected element is the function _freeze of the file libs/langgraph/langgraph/_internal/_cache.py of the component Task Result Cache. This manipulation of the argument default_cache_key causes use of weak h…
In MLflow versions prior to 3.14.0, when running with authentication enabled, the trace API endpoints lack proper authorization validators. This allows any authenticated user to bypass experiment-level authorization controls on all trace operations, including reading, deleting, a…
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, …
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…
A vulnerability has been found in MLflow up to 4666cffc7912ea606d592fc38d6a75e2935f65e7. The impacted element is an unknown function of the component Experiment-scoped Label Schema CRUD API. Such manipulation leads to missing authorization. It is possible to launch the attack rem…
Unauthenticated SQL Injection in Quotes llama <= 3.1.5 versions.
LangChain is a framework for building agents and LLM-powered applications. Prior to 1.3.9, several LangChain components that resolve filesystem paths or expand search patterns do not consistently confine the resolved path to the intended root directory. Affected behaviors include…
Vulnerability in the Siebel CRM Deployment product of Oracle Siebel CRM (component: Database Upgrade). Supported versions that are affected are 17.0-26.5. Easily exploitable vulnerability allows low privileged attacker with logon to the infrastructure where Siebel CRM Deployment…
Vulnerability in the Identity Manager Connector product of Oracle Fusion Middleware (component: Database User). Supported versions that are affected are 12.2.1.4.0 and 14.1.2.1.0. Easily exploitable vulnerability allows low privileged attacker with network access via HTTP to co…
Datadog, Inc Vector v0.54.0 was discovered to contain a SQL injection vulnerability in the set_uri_query parameter in the KeyPartitioner::partition function. This vulnerability allows attackers to access sensitive database information via crafted SQL statements.
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.