GPT-OSS-120B profile

    GPT-OSS-120B — security & risk dashboard

    Known weaknesses, safety and security advisories, and documented real-world incidents for GPT-OSS-120B — collected automatically and re-checked every few hours, so teams building on it can see what to design around.

    Last checked 27 Oct 2026

    Ask the Advisor about this model
    Known flaws

    5

    Security risks

    3

    Real-world incidents

    0

    Advisories logged

    0

    Security, safety & abuse risks

    • Modified or fine-tuned weights may change safety behavior; downstream deployments require independent safety evaluation.
    • Tool-connected deployments can turn incorrect or adversarially influenced outputs into consequential actions unless permissions and execution are constrained.
    • Plausible factual errors can mislead users in medical, legal, financial and other high-stakes applications.

    Known flaws & limitations

    • Text-only model; it does not natively process images, audio or video.
    • Can hallucinate factual answers; OpenAI reports higher hallucination rates than some proprietary reasoning models.
    • Correct integration requires support for Harmony’s conversation structure, roles, channels and tool conventions.
    • The documented single-GPU deployment requires 80 GB of GPU memory, exceeding most consumer graphics cards.
    • Tool-assisted benchmark results depend on the associated tools, execution environment and evaluation settings.

    Security advisories & risk updates

    No risk advisories logged since this profile started being tracked. New ones appear here automatically.

    What this means if you are building on it

    • Native image, audio or video understanding.
    • Unsupervised high-stakes advice or decisions requiring consistently reliable factual accuracy.
    • Unrestricted autonomous execution with access to sensitive systems or data.
    • Local deployment on typical consumer GPUs without substantial deployment changes.

    Everything here comes from published documentation, advisories and reporting, with links to the original sources. It is not a complete vulnerability database — always check the provider's own security notices before shipping.