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.
Langflow 1.0.16 before 1.12.0 and 0.0.94 before 1.12.0 contain an unsafe eval() vulnerability in schema.py that allows authenticated attackers to achieve code execution by placing a Python object with a malicious __repr__ method into component input options lists. The eval() sink…
A flaw has been found in langchain4j up to 1.5.3-beta10/1.11.10-beta18/1.18.1-beta27. This vulnerability affects the function AgenticScopeSerializer.fromJson of the file AgenticScopeJsonSerializationIT.java of the component LangChain4j-agentic. This manipulation causes deserializ…
LangChain MongoDB provides integrations between MongoDB, Atlas, LangChain, and LangGraph. Prior to langgraph-checkpoint-mongodb 0.3.0 and langgraph-store-mongodb 0.4.0, MongoDBSaver.list(), MongoDBSaver.alist(), and MongoDBStore.search() incorporate filter dictionaries into Mongo…
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…
Hugging Face PyTorch Image Models checkpoint Deserialization of Untrusted Data Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Hugging Face PyTorch Image Models. User interaction is required to…
MLflow is an open source AI engineering platform for agents, large language models, and machine learning models. Prior to 3.15.0, CreateModelVersion accepts a run_id or model_id after _validate_source_run() or _validate_source_model() in mlflow/server/handlers.py verifies only pa…
MLflow is an open source AI engineering platform for agents, large language models, and machine learning models. From 3.13.0 until 3.15.0, LogInputs is absent from BEFORE_REQUEST_HANDLERS in the mlflow/server/auth package, allowing any authenticated user to call POST /api/2.0/mlf…
MLflow is an open source AI engineering platform for agents, large language models, and machine learning models. Starting in 3.3.0 and 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…
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…
The native inference process that Elasticsearch uses to evaluate uploaded machine learning models accepts a model operation that computes a memory address from an offset supplied inside the model, without validating that the offset stays within the bounds of the underlying storag…
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…
A vulnerability in keras-team/keras versions <= 3.15.0 allows for a denial of service (DoS) attack when loading malicious .keras model files via the keras.models.load_model() function. The H5IOStore.__getitem__ method in keras/src/saving/saving_lib.py does not validate the shape …
A vulnerability in `nltk.downloader` in nltk/nltk versions <= 3.9.4 allows for cross-package resource and model poisoning. The downloader extracts package archives into shared namespaces such as `corpora/` and `taggers/` instead of package-isolated roots, and validates package in…
llama.cpp builds b1886 through b7445 contain a double free vulnerability in the LLaMA-Android JNI wrapper where new_1batch() allocates memory using malloc() while free_1batch() deallocates it using the C++ delete operator, causing heap metadata corruption. Attackers can trigger t…
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 was determined in ggml-org llama.cpp e15efe0. Affected by this issue is some unknown functionality of the file common/jinja/parser.cpp of the component Jinja Minja Template Parser. Executing a manipulation with the input {{9|9|{ can lead to reachable assertion. Th…
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…
Vulnerability in the RDBMS component of Oracle Database Server. Supported versions that are affected are 19.3-19.31, 21.3-21.22 and 23.4.0-23.26.2. Easily exploitable vulnerability allows high privileged attacker having None privilege with network access via Oracle Net to compr…
Vulnerability in the RDBMS component of Oracle Database Server. Supported versions that are affected are 19.3-19.31, 21.3-21.22 and 23.4.0-23.26.2. Easily exploitable vulnerability allows unauthenticated attacker with network access via Oracle Net to compromise RDBMS. While th…
FileBrowser Quantum is a free, self-hosted, web-based file manager. Prior to version 1.4.3-beta, the `subtitlesHandler` endpoint (`GET /api/media/subtitles`) accepts two user-controlled query parameters: `path` and `name`, both of which are used in filesystem operations without s…
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…
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.