CVE-2026-70660

Read full 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. Prior to master-764-e22272e, the safetensors loader in src/model_io/safetensors_io.cpp trusts each tensor's data_offsets after checking only that nbytes equals end - begin. A crafted .safetensors file can declare a byte range beyond the file's data section, causing src/model_loader.cpp to consume an attacker-chosen length from an unchecked mapped-file offset. Loading the model can read adjacent process memory into tensor buffers or crash the process. This issue is fixed in master-764-e22272e.

CVSS 6.9 (MEDIUM)

Attention and evidence

HYPE SCORE

0.0/10

REALITY · THREAT PRIORITY

2.4–4.9/10

Missing inputs: range of priority

Evidence confidence: Insufficient evidence

Why this priority?

Technical severity: CVSS 6.9: +2.42

Fresh prediction unavailable

General review priority, not probability, victim count or asset-specific risk. A range covers missing CVSS/EPSS inputs within the current evidence state.

Sources: 1 documents and public datasets.

Hype components

Headline sample (25%)

0/100

Press, 30 days (60%)

0/100

Grounded branding (15%)

0/100

HYPE TOTAL0/100

Sources and documents

Latest Vulnerabilities

Technical advisory · 05 Nov 2026, 16:17 · CVE-2026-70660 - stable-diffusion.cpp: Out-of-bounds read in safetensors loader: unvalidated data_offsets allow a tensor's byte range to extend past the end of the file

Score evolution

● Hype ● Reality

First record: hype 0.0 · reality 2.4 (2026-11-05 17:25). The curve appears once the score changes.

Public exploit evidence

Public exploit entries / repo candidates

Evidence context and dated references

Reality is general threat/review priority, combining observed exploitation, CVSS severity and fresh EPSS. Evidence confidence is separate. This is not calibrated risk, a victim count or an asset-specific assessment. A range reflects missing numeric inputs. Published 1 days ago. Exploitation evidence usually takes weeks to show up: a low reality score can mean there is no data yet, not that the flaw is mild.

Evidence in context

Confidence in exploitation evidence: Insufficient evidence
Priority basis: Exploitation in attacks unconfirmed; CVSS 6.9; fresh prediction unavailable
Attention, last 30 days: 0 distinct story titles; 0 press documents; 0 publisher domains.
Technical potential: local access, no prior privileges, passive user interaction.
Observed activity: No exploitation observation is recorded.
Known scale: Not quantified.
Evidence confidence basis: Insufficient evidence

Score evaluated: 2026-11-05 17:25:03.612586+00:00 · EPSS snapshot: not available

Source event timeline

Published

05 Nov 2026, 15:27

Score calculated

05 Nov 2026, 17:25