Browse / Unbounded Consumption
Unbounded Consumption
Denial of service, resource exhaustion and cost attacks. 117 records. Reference: OWASP LLM10 · ATLAS AML.T0029.
- Uncontrolled resource consumption 34
- Other denial of service 31
- Denial of service 18
- Regular expression denial of service 16
- Allocation without limits 12
- Uncontrolled recursion 4
- Decompression bomb 2
- NLTK: Quadratic-time CPU denial of service in Tree.chomsky_normal_form right-factor binarization via list.pop(0)
- NLTK: Quadratic-time CPU denial of service in ConllCorpusReader SRL instance builder via nested span rescan
- vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool A single short chat template with unbounded Jinja2 rendering runs in a limited worker pool that cannot be interrupted, blocking chat endpoints for all tenants.
- vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine A legal maximum-length audio clip makes the Phi-4 audio encoder keep full attention matrices for every layer in memory, exhausting GPU memory and crashing the engine.
- vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
- vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs
- vllm p2p never connected zmq_exhaustion Repeated API requests naming many unreachable peer addresses leave ZeroMQ sockets open, exhausting the socket quota and crashing the inference engine.
- vLLM : DoS via unvalidated mm_processor_kwargs in multimodal image processors (Isaac, InternVL, H2OVL, etc.)
- Pydantic AI: Concurrency-limited models can keep their slot when a streamed request ends early Streams that end early or are consumed from another task fail to release shared concurrency slots, so repeated disconnects gradually block other requests.
- Pydantic AI: Event loop blocked by quadratic title extraction in `web_fetch` An attacker who can steer the agent's web fetch tool to a crafted page causes quadratic processing that blocks the event loop.
- Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl
- Pydantic AI: Excessive resource use when local web fetching converts nested HTML
- vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service One request with a cache_salt containing a forbidden character passes loose validation and raises an uncaught error that kills the vLLM engine process.
- vLLM: GLMGA video sampling permits request-driven CPU and memory exhaustion
- vLLM: Qwen2-VL / Qwen3-VL video samplers bound on request-controlled max_frames, which the num_frames ceiling does not reach
- vm2: Host-returned Promise rejection can bypass vm2's unhandled-rejection hardening and terminate the host process
- vm2: timeout Option Bypass via FinalizationRegistry Cleanup Callback (Unbounded Host Event-Loop Block)
- vLLM: Request-selected PyNvVideoCodec GPU decode bypasses static VRAM reservation A client can pick a GPU video decoder per request, allocating GPU memory the engine never reserved and exhausting VRAM.
- vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions
- n8n: Unauthenticated Persistent Storage Exhaustion via OAuth Dynamic Client Registration Endpoint
- n8n: Regular Expression Denial of Service in the Default Blocked-File-Pattern Match via a Git Node Clone Path
- NLTK: ReDoS in nltk.text.Text.findall() via unvalidated user-supplied regular expressions
- NLTK: ReDoS in nltk.tgrep via unvalidated user-supplied regular expressions
- vLLM: ReDoS via structured_outputs.regex in the lm-format-enforcer backend (no compile timeout) — missed sibling of GHSA-rwxx-mrjm-wc2m A structured output request with a catastrophic regex is compiled without a timeout in the lm-format-enforcer backend, stalling the inference worker.
- vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds Derender routes detokenize client-supplied token ID lists without output size or count limits, consuming CPU and memory.
- NLTK: Uncontrolled resource consumption in RecursiveDescentParser via ambiguous or left-recursive grammars
- NLTK: Quadratic CPU Exhaustion in `XMLCorpusView._read_xml_fragment()`
- NLTK: Quadratic-time DoS in PorterStemmer via long runs of 'y'
- NLTK TweetTokenizer vulnerable to denial of service through catastrophic regex backtracking
- New API: Unauthenticated payment webhooks allow memory and disk DoS via unbounded body reads and full-body logging
- vm2's bufferAllocLimit cap bypassed by Buffer.concat and Buffer.from arrayLike
- vm2 has Memory Exhaustion DoS via bufferAllocLimit Bypass
- vLLM: Completion prompt lists fan out into unbounded engine requests A completions request with a list of prompts is expanded into one engine generator per element with no outer count limit, so one request spawns many backend subrequests.
- Open WebUI: Any authenticated user can stall a worker via a knowledge-search pattern that backtracks catastrophically A chat user can get the model to run a catastrophic-backtracking regex against knowledge files, and no timeout stops it from pinning a worker.
- Natural Language Toolkit (NLTK): ReDoS in NLTK ReviewsCorpusReader FEATURES regex
- n8n: Authenticated Users Can Exhaust Temporary Disk Storage via Data-Table File Uploads
- vLLM denial of service via prompt embeds on M-RoPE models A prompt-embeds request to completions on an M-RoPE model trips an assertion that crashes the engine and the whole server.
- vLLM has Remote DoS via Invalid Recovered Token Reinjection An overlapping generate and abort sequence makes speculative decoding feed an out-of-vocabulary sentinel token back into the drafter, crashing the shared worker.
- vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines backends
- vLLM: Speech-to-text upload size limit is enforced after full UploadFile read
- Langflow: Unauthenticated DoS through multipart form boundary file upload
- vLLM: OOM Denial of Service via Audio Decompression Bomb A small compressed audio upload decodes into a very large float buffer, exhausting server memory because the size check only applies to compressed bytes.
- vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels Temperature checks use comparisons that let NaN and positive infinity through, so these values reach GPU sampling kernels and crash the inference worker.
- n8n: Denial of Service via ZIP decompression in webhook workflow
- vLLM is vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method
- Docling: Unsafe Archive Extraction and XML Parsing in METS-GBS Backend
- vm2 has a Sandbox Escape via Promise Constructor Unhandled Rejection (Process Crash DoS)
- FastChat has Denial of Service Through Blocking Event Loop in Model Workers (Incomplete Fix for ff66426)
- PraisonAI: Unauthenticated WebSocket Endpoint Proxies to Paid OpenAI Realtime API Without Rate Limits
- vLLM: Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server An unauthenticated request with an enormous n value makes the API server copy request objects until it blocks the event loop and runs out of memory.