ai_security▌

← feed

NOTABLE

CVE-2026-122160: AIlice agent framework loads models from untrusted control spheres

GHSA-6wf7-9xfh-x657: AIlice up to 0.4.0 passes base_model_name_or_path through its HuggingFace model wrapper (LoadModel_PEFT), including functionality from an untrusted control sphere; remotely attackable with a public PoC attached to the source report. GHSA rates it low.

released 2026-11-05 · ingested 2026-11-08T18:40Z

Sources

Primary source · corroboration

Cite this

APA

AI Security Index. (2026). CVE-2026-122160: AIlice agent framework loads models from untrusted control spheres. AI Security Index. https://github.com/advisories/GHSA-6wf7-9xfh-x657

BibTeX

@misc{aisec-2026-11-05-ailice-untrusted-model-load-ghsa-6wf7-9xfh-x657,
  title  = {CVE-2026-122160: AIlice agent framework loads models from untrusted control spheres},
  year   = {2026},
  howpublished = {\url{https://github.com/advisories/GHSA-6wf7-9xfh-x657}},
  note   = {AI Security Index item 2026-11-05-ailice-untrusted-model-load-ghsa-6wf7-9xfh-x657}
}