CVE-2026-112080 LlamaChinese CVE debrief

Who should care

Defenders responsible for LlamaChinese Llama-Chinese deployments, operators, and security teams should assess exposure, verify inventory for potential vulnerability, and prioritize verifying the presence of affected versions in their inventory due to unclear version information for affected or updated releases.

Why it matters

Defenders should prioritize verifying the presence of affected versions in their inventory and assessing exposure due to the unclear version information for affected or updated releases.

• Verify inventory for affected versions
• Assess exposure to vulnerable component
• Monitor for exploitation attempts

Technical summary

The vulnerability is located in the get_class_from_dynamic_module function of the examples/chat_gradio_no_merge.py file in the Adapter Config component of LlamaChinese Llama-Chinese up to 6fa0fffb0dd82fe3cfaa1449ee54a5806d26ae9b. The manipulation of the base_model_name_or_path argument leads to code injection, allowing remote attacks. The exploit has been made public and could be used. Defenders should assess the unclear version information for affected or updated releases due to the product's rolling release system.

Defensive priority

Defenders should prioritize verifying the presence of affected versions in their inventory and assessing exposure, as the product utilizes a rolling release system for continuous delivery, making version information for affected or updated releases unclear.

Recommended defensive actions

• Verify the presence of affected LlamaChinese Llama-Chinese versions in inventory
• Assess exposure to the vulnerable Adapter Config component
• Monitor for potential exploitation attempts
• Review compensating controls for exposed systems
• Check relevant monitoring and detection logs for exposed assets
• Track exceptions and retest remediated assets
• Plan vendor-supported updates or mitigations through normal change control

Evidence notes

The CVE record and NVD entry provide details on the vulnerability, including its description, CVSS score, and affected component. However, the exact versions affected are not disclosed due to the product's rolling release system.

Sources and references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.