Browse / AI Framework and Platform Flaws / Unsafe deserialisation
Unsafe deserialisation
8 records in AI Framework and Platform Flaws.
- Feast vulnerable to unsafe deserialization RCE in registry server via UDF proto The registry server runs dill.loads on a base64 UDF body before any authorisation check, so a crafted object with a malicious __reduce__ executes OS commands.
- FoundationAgents MetaGPT: Deserialization through flawed argument mapping via Message.check_instruct_content() Manipulated argument mapping in Message.check_instruct_content leads to unsafe deserialisation of attacker-controlled data during local execution.
- SGLanG: Multimodal scheduler deserializes untrusted pickle data on 0.0.0.0 ROUTER socket The scheduler's socket listens on all interfaces and unpickles incoming messages, so a remote sender can execute code.
- LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs Serialization does not escape dictionaries with the reserved lc key, so attacker-supplied data is later rebuilt as framework objects, which can expose secrets.
- Remote Code Execution Vulnerability in vLLM Multi-Node Cluster Configuration Secondary vLLM hosts unpickle messages received over ZeroMQ, so anyone who controls the primary host or its network can run code on them.
- BentoML deserialization vulnerability Setting the args-number parameter above 1 on the BentoML runner server causes attacker-supplied data to be deserialised, executing arbitrary code.
- vLLM allows Remote Code Execution by Pickle Deserialization via AsyncEngineRPCServer() RPC server entrypoints The RPC server passes incoming network messages directly to cloudpickle loads, so a crafted message executes code when it is deserialised.
- TorchServe Pre-Auth Remote Code Execution An outdated SnakeYAML library lets crafted YAML instantiate Java objects in TorchServe, enabling code execution without authentication.