vLLM: Request-controlled mm_processor_kwargs.code_revision allows remote code execution
Affects: vLLM
Sourced advisories. Plain-language scorecards. Free tools for small teams.
Securaity tracks security and safety problems in AI software and services, rates how serious they are, and says in plain language who is affected and what to do.
Every fact dated and linked to its source.
Affects: vLLM
Affects: LiteLLM
Affects: LiteLLM
Affects: LiteLLM
Affects: MLflow
Every day we pull new vulnerability records for popular AI software from public databases.
Each record is matched to a named product and checked against its original source.
Severity follows the published CVSS score, from Critical down to Info.
Each advisory names the affected product and links to the source with fix details.
Records are checked daily, and changes at the source update the advisory.
Every advisory links to the public record it comes from.
Every advisory shows when we published it and when the source last changed.
Short, clear pages for the people who have to decide.
Every page is free to read, with no sign-up.
What popular AI tools do with your data, and the settings to change first.
A free course in ten short lessons for small teams that use AI.
Frameworks, policies and attacks explained in plain language.
Short definitions of the AI security terms you will meet.
What the advisories show, and how to put them to work.
Advisory counts and an RSS feed for each AI product we track.