PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-116608 DAMO Academy CVE debrief

AI-assisted PatchSiren debrief based on the supplied source corpus. The CVE record was published on 2026-10-27T00:15:18.298Z and has not been modified since then. The vulnerability affects DAMO Academy VideoLLaMA2 up to 1.1, specifically the load_pretrained_model function in videollama2/model/__init__.py, allowing for remote exploitation due to improper validation of integrity check value. Defenders should assess exposure and verify model loading integrity. The project was informed early but has not responded yet.

Vendor
DAMO Academy
Product
VideoLLaMA2
CVSS
MEDIUM 5.3
CISA KEV
Not listed in stored evidence
Original CVE published
2026-10-27
Original CVE updated
2026-11-02
Advisory published
2026-10-27
Advisory updated
2026-11-02

Who should care

Defenders responsible for DAMO Academy VideoLLaMA2 deployments should assess exposure and verify the integrity of model loading, especially in environments where remote exploitation is a concern, due to improper validation of integrity check value. They should also review compensating controls for exposed systems while remediation is scheduled and verified.

Why it matters

Defenders should prioritize verifying the integrity of model loading in DAMO Academy VideoLLaMA2, especially in environments where remote exploitation is a concern, due to improper validation of integrity check value.

  • Remote exploitation is possible
  • Improper validation of integrity check value can lead to security risks
  • Verify the integrity of model loading to prevent potential security breaches

Technical summary

A security vulnerability has been detected in DAMO Academy VideoLLaMA2 up to 1.1. The function load_pretrained_model of the file videollama2/model/__init__.py has improper validation of integrity check value, allowing for remote exploitation. The project was informed of the problem early through an issue report but has not responded yet. Defenders should prioritize verifying the integrity of model loading in DAMO Academy VideoLLaMA2, especially in environments where remote exploitation is a concern, due to improper validation of integrity check value.

Defensive priority

Defenders should prioritize verifying the integrity of model loading in DAMO Academy VideoLLaMA2, especially in environments where remote exploitation is a concern.

Recommended defensive actions

  • Verify the integrity of model loading in DAMO Academy VideoLLaMA2
  • Restrict access to the load_pretrained_model function
  • Monitor for potential exploitation attempts
  • Review compensating controls for exposed systems while remediation is scheduled and verified
  • Check relevant monitoring, detection, and logs for exposed assets that need extra review
  • Track exceptions, retest remediated assets, and close the item only after evidence is documented
  • Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up

Evidence notes

The CVE record and source item provide details on the vulnerability in DAMO Academy VideoLLaMA2. The exploit has been disclosed publicly, but there is no information on in-the-wild exploitation. The vulnerability allows remote exploitation due to improper validation of integrity check value in the load_pretrained_model function of videollama2/model/__init__.py. Defenders should verify the integrity of model loading, especially in environments where remote exploitation is a concern.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-116608 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-116608

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-116608 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-116608

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

  • DAMO Academy VideoLLaMA2 Model Loading __init__.py load_pretrained_model integrity check

    Unverified legacy reference

    URL: https://raw.githubusercontent.com/CVEProject/cvelistV5/main/cves/2026/116xxx/CVE-2026-116608.json

    cve_program_cvelist_v5

  • Source reference

    Unverified legacy reference

    URL: https://vuldb.com/vuln/426516

    Supplemental source - vdb-entry, technical-description

  • Source reference

    Unverified legacy reference

    URL: https://vuldb.com/vuln/426516/cti

    Supplemental source - signature, permissions-required

  • Source reference

    Unverified legacy reference

    URL: https://vuldb.com/cve/CVE-2026-116608

    Supplemental source - third-party-advisory

  • Source reference

    Unverified legacy reference

    URL: https://vuldb.com/submit/1022955

    Supplemental source - third-party-advisory

  • Source reference

    Unverified legacy reference

    URL: https://github.com/DAMO-NLP-SG/VideoLLaMA2/issues/182

    Supplemental source - exploit, issue-tracking

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.