Skip to content

LocalAI

v4.2.5 Security

This release includes 1 security fix for security teams reviewing exposed deployments.

Published 18d Model Serving & MLOps
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →
This release patches 1 known CVE

Topics

agents ai api audio-generation decentralized distributed
+12 more
image-generation libp2p llama llm mamba mcp musicgen object-detection rerank stable-diffusion text-generation tts

Affected surfaces

deps

Summary

AI summary

Fixed nil filter guard in Ollama gallery model listing and accepted float‑encoded integer options.

Changes in this release

Security Medium

Close Hugging Face scan response body to prevent information leakage.

Close Hugging Face scan response body to prevent information leakage.

Source: llm_adapter@2026-05-21

Confidence: high

Security Medium

Bump gomarkdown/markdown to mitigate GHSA-77fj-vx54-gvh7 vulnerability.

Bump gomarkdown/markdown to mitigate GHSA-77fj-vx54-gvh7 vulnerability.

Source: llm_adapter@2026-05-21

Confidence: low

Feature Medium

Expose 12 missing common_params via options[] for llama-cpp.

Expose 12 missing common_params via options[] for llama-cpp.

Source: llm_adapter@2026-05-21

Confidence: high

Feature Medium

Validate video image URLs before download.

Validate video image URLs before download.

Source: llm_adapter@2026-05-21

Confidence: high

Feature Medium

Update Swagger documentation for LocalAI.

Update Swagger documentation for LocalAI.

Source: llm_adapter@2026-05-21

Confidence: high

Dependency Medium

Bump ggml-org/llama.cpp to `7f3f843c31cd32dc4adc10b393342dfee071c332`.

Bump ggml-org/llama.cpp to `7f3f843c31cd32dc4adc10b393342dfee071c332`.

Source: llm_adapter@2026-05-21

Confidence: low

Dependency Medium

Update antirez/ds4 to `04b6fda2be395094cbf2d20d921e7a705a4166ef`.

Update antirez/ds4 to `04b6fda2be395094cbf2d20d921e7a705a4166ef`.

Source: llm_adapter@2026-05-21

Confidence: low

Dependency Medium

Update ggml-org/whisper.cpp to `46ca43d6399fdeada1b49fb2126ba373bd9ebc38`.

Update ggml-org/whisper.cpp to `46ca43d6399fdeada1b49fb2126ba373bd9ebc38`.

Source: llm_adapter@2026-05-21

Confidence: low

Dependency Medium

Update ikawrakow/ik_llama.cpp to `0fcffdb64d21e57f0778f342415754156e01adfa`.

Update ikawrakow/ik_llama.cpp to `0fcffdb64d21e57f0778f342415754156e01adfa`.

Source: llm_adapter@2026-05-21

Confidence: low

Dependency Medium

Update vllm-project/vllm cu130 wheel to `0.21.0`.

Update vllm-project/vllm cu130 wheel to `0.21.0`.

Source: llm_adapter@2026-05-21

Confidence: low

Dependency Medium

Bump ikawrakow/ik_llama.cpp to `5cc0d86c760e9858e4bed4418400bb39dbe025f2`.

Bump ikawrakow/ik_llama.cpp to `5cc0d86c760e9858e4bed4418400bb39dbe025f2`.

Source: llm_adapter@2026-05-21

Confidence: low

Dependency Medium

Update antirez/ds4 to `950e8e6474a1c9fabe04e669d607606a7ef8824f`.

Update antirez/ds4 to `950e8e6474a1c9fabe04e669d607606a7ef8824f`.

Source: llm_adapter@2026-05-21

Confidence: low

Dependency Medium

Update ggml-org/whisper.cpp to `968eebe77225d25e57a3f981da7c696310f0e881`.

Update ggml-org/whisper.cpp to `968eebe77225d25e57a3f981da7c696310f0e881`.

Source: llm_adapter@2026-05-21

Confidence: low

Dependency Medium

Bump ggml-org/llama.cpp to `1348f67c58f561808136e8a152a9eddec168f221`.

Bump ggml-org/llama.cpp to `1348f67c58f561808136e8a152a9eddec168f221`.

Source: llm_adapter@2026-05-21

Confidence: low

Bugfix Medium

Guard nil filter in galleryop.ListModels fixes issue #9817.

Guard nil filter in galleryop.ListModels fixes issue #9817.

Source: llm_adapter@2026-05-21

Confidence: high

Bugfix Medium

Honor output_modalities to skip TTS in text-only mode for realtime streaming.

Honor output_modalities to skip TTS in text-only mode for realtime streaming.

Source: llm_adapter@2026-05-21

Confidence: high

Bugfix Medium

Accept float-encoded integer options in ollama, fixing issue #9837.

Accept float-encoded integer options in ollama, fixing issue #9837.

Source: llm_adapter@2026-05-21

Confidence: high

Bugfix Medium

Comply with OpenAI usage / stream_options spec for streaming.

Comply with OpenAI usage / stream_options spec for streaming.

Source: llm_adapter@2026-05-21

Confidence: high

Bugfix Medium

Validate archive member paths before extraction.

Validate archive member paths before extraction.

Source: llm_adapter@2026-05-21

Confidence: high

Other Medium

Update LocalAI documentation version by @localai-bot.

Update LocalAI documentation version by @localai-bot.

Source: llm_adapter@2026-05-21

Confidence: low

Full changelog

What's Changed

Bug fixes :bug:

  • fix(ollama): guard nil filter in galleryop.ListModels (#9817) by @localai-bot in https://github.com/mudler/LocalAI/pull/9836
  • realtime: honor output_modalities to skip TTS in text-only mode by @localai-bot in https://github.com/mudler/LocalAI/pull/9838
  • fix(ollama): accept float-encoded integer options (fixes #9837) by @localai-bot in https://github.com/mudler/LocalAI/pull/9849

Other Changes

  • chore: :arrow_up: Update ggml-org/llama.cpp to 7f3f843c31cd32dc4adc10b393342dfee071c332 by @localai-bot in https://github.com/mudler/LocalAI/pull/9809
  • feat(llama-cpp): expose 12 missing common_params via options[] by @localai-bot in https://github.com/mudler/LocalAI/pull/9814
  • fix(streaming): comply with OpenAI usage / stream_options spec by @localai-bot in https://github.com/mudler/LocalAI/pull/9815
  • Close Hugging Face scan response body by @massy-o in https://github.com/mudler/LocalAI/pull/9818
  • Validate video image URLs before download by @massy-o in https://github.com/mudler/LocalAI/pull/9819
  • feat(swagger): update swagger by @localai-bot in https://github.com/mudler/LocalAI/pull/9824
  • chore: :arrow_up: Update antirez/ds4 to 04b6fda2be395094cbf2d20d921e7a705a4166ef by @localai-bot in https://github.com/mudler/LocalAI/pull/9830
  • chore: :arrow_up: Update ggml-org/whisper.cpp to 46ca43d6399fdeada1b49fb2126ba373bd9ebc38 by @localai-bot in https://github.com/mudler/LocalAI/pull/9829
  • chore: :arrow_up: Update ikawrakow/ik_llama.cpp to 0fcffdb64d21e57f0778f342415754156e01adfa by @localai-bot in https://github.com/mudler/LocalAI/pull/9828
  • docs: :arrow_up: update docs version mudler/LocalAI by @localai-bot in https://github.com/mudler/LocalAI/pull/9825
  • chore: :arrow_up: Update leejet/stable-diffusion.cpp to 0b8296915c4094090cff6bd2e09a5e98288c3c7d by @localai-bot in https://github.com/mudler/LocalAI/pull/9827
  • chore: :arrow_up: Update ggml-org/llama.cpp to 834a243664114487f99520370a7a7b00fc7a486f by @localai-bot in https://github.com/mudler/LocalAI/pull/9826
  • Validate archive member paths before extraction by @massy-o in https://github.com/mudler/LocalAI/pull/9820
  • fix(deps): bump gomarkdown/markdown for GHSA-77fj-vx54-gvh7 by @richiejp in https://github.com/mudler/LocalAI/pull/9841
  • chore: :arrow_up: Update vllm-project/vllm cu130 wheel to 0.21.0 by @localai-bot in https://github.com/mudler/LocalAI/pull/9846
  • chore: :arrow_up: Update ikawrakow/ik_llama.cpp to 5cc0d86c760e9858e4bed4418400bb39dbe025f2 by @localai-bot in https://github.com/mudler/LocalAI/pull/9845
  • chore: :arrow_up: Update antirez/ds4 to 950e8e6474a1c9fabe04e669d607606a7ef8824f by @localai-bot in https://github.com/mudler/LocalAI/pull/9844
  • chore: :arrow_up: Update ggml-org/whisper.cpp to 968eebe77225d25e57a3f981da7c696310f0e881 by @localai-bot in https://github.com/mudler/LocalAI/pull/9843
  • chore: :arrow_up: Update ggml-org/llama.cpp to 1348f67c58f561808136e8a152a9eddec168f221 by @localai-bot in https://github.com/mudler/LocalAI/pull/9842

New Contributors

  • @massy-o made their first contribution in https://github.com/mudler/LocalAI/pull/9818

Full Changelog: https://github.com/mudler/LocalAI/compare/v4.2.4...v4.2.5

Security Fixes

  • dep: GHSA-77fj-vx54-gvh7 — bump gomarkdown/markdown

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track LocalAI

Get notified when new releases ship.

Sign up free

About LocalAI

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

All releases →

Related context

Beta — feedback welcome: [email protected]