CVE-2026-47748

medium
Published 2026-06-16 ยท Modified 2026-06-16
CVSS v3
5.5
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
CVSS v4 NEW
โ€”
not yet in upstream
VIR risk
5.5

Description

stable-diffusion.cpp is a pure C/C++ library for running diffusion model (Stable Diffusion, Flux, Wan, Qwen Image, Z-Image, and more) inference. Versions prior to master-584-0a7ae07 are vulnerable to an out-of-bounds reads error through PyTorch checkpoint pickle opcode parsing. The pickle .ckpt parser in src/model.cpp did not consistently check that enough input remained before reading opcode arguments or advancing the parser buffer with a crafted or truncated .ckpt file. Throughout the pickle parser, opcode handlers advanced the parser position with expressions such as buffer += N without first checking that buffer + N <= buffer_end. A truncated file could therefore cause reads past the end of the metadata buffer. LibFuzzer found crashes in under one second using malformed checkpoint inputs. Any application using affected stable-diffusion.cpp releases to load untrusted .ckpt model files could be vulnerable. The attack requires the victim or application to load a .ckpt file from an untrusted source, such as a downloaded model from a model sharing site. This issue has been fixed in version master-584-0a7ae07. If developers are unable to immediately update their applications, they can work around this issue by ensuring they do not load .ckpt checkpoint files from untrusted sources. They should prefer trusted model sources and safer formats such as .safetensors where possible.

Predictions

Exploit likelihood
55%
Patch ETA
โ€”

Heuristic predictions, AS-IS, for prioritization only.

Mitigations

No mitigations published for this CVE yet.

The vendor-content worker queues fetches as references arrive (check back in a few minutes). Or โ€” if you've already worked around this in production โ€” publish your fix to the community-verified tier.

โœš Propose a mitigation on Community โ†’ Mitigations published via the community go through AI scoring + 2 human reviewers + 7-day silent objection window before landing here with source_tier=community-verified.

References

CWEs

CWE-125

Community-verified mitigations for this CVE will appear above when contributors publish them.

Verify integrity in audit chain (admin only). AS-IS.