HighVulnerability
CVE-2026-73325: OneCompression library unsafe deserialization via crafted model.pt checkpoint
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-73325
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.4%
Summary
Fujitsu Research's OneCompression library 1.2.0 has an unsafe deserialization flaw, tracked as CVE-2026-73325. QuantizedModelLoader.load_quantized_model_pt() calls torch.load with weights_only=False, which runs Python's pickle machinery on a model.pt checkpoint. An attacker who supplies a crafted checkpoint with a malicious __reduce__ method can execute arbitrary Python code, including system commands, when the library loads it from a caller-selected model directory.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Related items
- MediumDetecting sleeper agents hiding in AI model neuronsSimilar attack · Microsoft Security Blog
- InfoStealthyPoison: Manipulating LLM Agent Behavior through Procedural Poisoning of Third-Party SkillsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
- MediumTop MCP security resources — November 2026Similar attack · Adversa AI Blog
- InfoThe Devil Wears Markdown: Detecting Malicious Intent Hidden in AI Agent Skill Instructions through Hybrid Static, Dynamic, and Agentic AnalysisSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
- MediumAI broke the cybersecurity world. What’s next?Similar attack · The Verge (AI)