InternLM vulnerabilities
We track 16 vulnerabilities in InternLM products across 2 products. 16 are rated high or critical, and none are known to be exploited. The most recent was published on November 9, 2026.
Latest InternLM vulnerabilities
- 7.5 High severity
lmdeploy: Server-Side Request Forgery
LMDeploy is a toolkit for compressing, deploying, and serving large language models. From 0.12.3 until 0.15.0, _is_safe_url validates remote media URLs with urlparse while requests.Session().get interprets backslashes differently when sending the request. An a
- 9.8 Critical severity
lmdeploy: Deserialization of Untrusted Data
InternLM LMDeploy 0.9.0 through 0.18.0 contains an unauthenticated remote code execution vulnerability that allows remote attackers to run OS commands by sending pickled data to the /update_weights endpoint. Attackers can submit a base64-encoded crafted pickle
- 10.0 Critical severity
MindSearch: Improper Neutralization of Special Elements in Output Used by a Downstream Component
A vulnerability has been found in InternLM MindSearch 0.1.0. This issue affects the function ExecutionAction.run of the file mindsearch/agent/graph.py of the component Planner Agent. The manipulation of the argument inputs leads to code injection. The attack c
- 8.8 High severity
lmdeploy: Uncontrolled Resource Consumption
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions 012.1 through 0.12.2 contain a code injection vulnerability in `lmdeploy/pytorch/config.py` line 620 that allows an attacker to execute arbitrary Python code by publi
- 9.8 Critical severity
lmdeploy: Deserialization of Untrusted Data
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.2 and prior to version 0.16.0, LMDeploy's PyTorch DistServe/PD-disaggregation control plane used `recv_pyobj()` to deserialize messages received throug
- 7.5 High severity
lmdeploy: Missing Release of Resource after Effective Lifetime
InternLM LMDeploy through 0.17.0 in DistServe prefill/decode disaggregation mode fails to release scheduler sessions because the proxy uses user-facing session IDs instead of internal scheduler keys. Unauthenticated attackers can send completion requests to th
- 7.5 High severity
lmdeploy: Reachable Assertion
InternLM LMDeploy through 0.17.0 contains a reachable assertion vulnerability in the DistServe decode migration loop that allows unauthenticated attackers to terminate the inference engine. Attackers can submit a migration_request with an empty remote_block_id
- 9.8 Critical severity
lmdeploy: Deserialization of Untrusted Data
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Starting in version 0.9.1 and prior to version 0.10.2, the LMdeploy implements an rpc server (AsyncRPCServer in zmq_rpc.py) for supporting the RPC communications. In its core
- 9.8 Critical severity
lmdeploy: Deserialization of Untrusted Data
LMDeploy deserializes disaggregated-serving peer messages with pickle. The handle_zmq_recv coroutine in lmdeploy/pytorch/disagg/conn/engine_conn.py reads peer-to-peer cache-free requests with recv_pyobj(), which deserializes the received bytes with pickle.load
- 8.6 High severity
lmdeploy: Server-Side Request Forgery
LMDeploy through 0.14.0, fixed in commit 03c3130, contains a server-side request forgery (SSRF) vulnerability in the _load_http_url function within the connection.py media handler, where the private-IP guard validates only the original URL without re-validatin
- 7.8 High severity
lmdeploy: Improper Control of Generation of Code
LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, hardcoded "trust_remote_code=True" enables HF supply-chain RCE without user opt-in. Version 0.13.0 patches the issue.
- 7.8 High severity
lmdeploy: Improper Control of Generation of Code
LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, LMDeploy is vulnerable to arbitrary code execution through hardcoded "trust_remote_code=True" in multiple HuggingFace model-loading call sites. A
- 7.5 High severity
lmdeploy: Server-Side Request Forgery
LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions prior to 0.12.3 have a Server-Side Request Forgery (SSRF) vulnerability in LMDeploy's vision-language module. The `load_image()` function in `lmdeploy/vl/utils.py` fe
- 8.8 High severity
lmdeploy: Deserialization of Untrusted Data
LMDeploy is a toolkit for compressing, deploying, and serving LLMs. Prior to version 0.11.1, an insecure deserialization vulnerability exists in lmdeploy where torch.load() is called without the weights_only=True parameter when loading model checkpoint files.
- 7.8 High severity
LMDeploy: Improper Control of Generation of Code
A vulnerability was found in InternLM LMDeploy up to 0.7.1. It has been declared as critical. Affected by this vulnerability is the function Open of the file lmdeploy/docs/en/conf.py. The manipulation leads to code injection. It is possible to launch the attac
- 7.8 High severity
LMDeploy: Deserialization of Untrusted Data
A vulnerability was found in InternLM LMDeploy up to 0.7.1. It has been classified as critical. Affected is the function load_weight_ckpt of the file lmdeploy/lmdeploy/vl/model/utils.py of the component PT File Handler. The manipulation leads to deserializatio