Severity by source
AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Network-reachable management endpoint is unauthenticated by default (PR:N) and the pickle fallback yields deterministic RCE (AC:L), giving full C/I/A impact on the host.
Primary rating from Vendor (certcc).
CVSS VectorVendor: certcc
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Lifecycle Timeline
4DescriptionCVE.org
SGLang contains a RCE vulnerability when attempting to load model weights from a HuggingFace repository, specifically within the /update_weights_from_disk, where torch.load(..., weights_only=False) fallback enables pickle deserialization of .bin files.
AnalysisAI
Remote code execution in SGLang (versions up to and including 0.5.15) allows attackers to run arbitrary code on the inference server by abusing the /update_weights_from_disk endpoint, which falls back to torch.load(..., weights_only=False) and thus deserializes attacker-controlled pickle streams embedded in .bin model-weight files. Because SGLang's HTTP serving API is typically exposed without authentication, an attacker able to reach the endpoint and influence the loaded weights path can achieve code execution as the serving process. …
Unlock full vulnerability intelligence
- Risk assessment & exploitation conditions
- Attack chain visualization
- Remediation with exact patch versions
- Threat intelligence from 22 sources
- Personal watchlist & email alerts
Free forever · No credit card required
Attack ChainAIDerived
Hypothetical attack flow derived from CVE metadata
Vulnerability AssessmentAI
| Exploitation | Exploitation requires reaching SGLang's /update_weights_from_disk endpoint and causing it to load an attacker-influenced legacy PyTorch .bin file, which triggers the torch.load(..., weights_only=False) pickle-deserialization fallback. … Additional conditions and limiting factors are described in the full assessment. |
| Risk Assessment | The signals are mixed and worth weighing carefully. … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in. |
| Exploit Scenario | An attacker who can reach an SGLang server's management API sends a request to /update_weights_from_disk pointing at a malicious .bin checkpoint (for example a booby-trapped HuggingFace repo or a path the attacker controls). When SGLang loads it via torch.load with weights_only=False, the embedded pickle gadget executes, giving the attacker code execution as the serving user. … |
| Remediation | Upgrade SGLang to a release newer than 0.5.15 that addresses GHSA-wf98-gv64-5wrf (consult the advisory at https://github.com/sgl-project/sglang/security/advisories/GHSA-wf98-gv64-5wrf for the exact fixed version; a released patched version is not independently confirmed from the provided data, so verify the fixed tag in the advisory before deploying). … Detailed patch versions, workarounds, and compensating controls in full report. |
Recommended ActionAI
Within 24 hours, identify all production and development SGLang deployments and document their current versions, network exposure, and data sensitivity. …
Sign in for detailed remediation steps and compensating controls.
Threat intelligence, references, and detailed analysis are available after sign-in.
Remote code execution in SGLang (versions up to and including 0.5.15) allows unauthenticated attackers to run arbitrary
SGLang's multimodal generation module deserializes untrusted data with pickle.loads() over an unauthenticated ZMQ broker
SGLang's encoder parallel disaggregation system is vulnerable to unauthenticated RCE through pickle deserialization in t
Unauthenticated remote code execution in SGLang (the LLM/multimodal generation serving runtime) affecting version 5.10 a
Remote code execution in SGLang 0.5.9's /v1/rerank endpoint allows unauthenticated attackers to execute arbitrary code b
Remote code execution in SGLang (versions ≤ v0.5.15) allows attackers to achieve arbitrary code execution through the op
Unauthenticated remote code execution affects SGLang, an LLM/multimodal inference-serving framework, at version 5.10, wh
Unauthenticated remote code execution in SGLang (versions 0 through 0.5.14) arises when the expert-parallel backup subsy
Arbitrary file write in SGLang's multimodal generation runtime (version 5.10) allows a remote, unauthenticated attacker
High severity vulnerability in SGLang. SGLangs `replay_request_dump.py` contains an insecure pickle.load() without valid
SGLang versions up to and including v0.5.15 expose unauthenticated network endpoints that allow complete model weight ex
Unauthenticated credential leakage in SGLang's /server_info HTTP endpoint exposes configured API keys and SSL keyfile pa
Same weakness CWE-502 – Deserialization of Untrusted Data
View allSame technique Deserialization
View allShare
External POC / Exploit Code
Leaving vuln.today
EUVD-2026-51264
GHSA-r344-357p-w9pp