v0.53.0

google-gemini/gemini-cliv0.53.0Jul 28, 2026by gemini-cli-robot

AI Summary

This release introduces a new LLM triage orchestrator and an evaluation coverage report command while addressing critical security vulnerabilities and credential handling issues. It includes significant improvements to macOS security profiles and fixes for infinite loops and prompt injection risks.

Key Highlights

Enforced workspace trust and task isolation to prevent Remote Code Execution (RCE)
Implemented new LLM triage orchestrator and container build capabilities
Added eval coverage report command to track evaluation metrics
Fixed infinite ReAct and prompt injection loops to improve stability

New Features

LLM triage orchestrator and container build
Eval coverage report command

Full Release Notes

## What's Changed
* fix(core,a2a): group cancelled tool responses and coalesce consecutive roles to prevent 400 Bad Request by @luisfelipe-alt in https://github.com/google-gemini/gemini-cli/pull/28407
* feat(caretaker-triage): implement LLM triage orchestrator and container build by @chadd28 in https://github.com/google-gemini/gemini-cli/pull/28345
* refactor(cli): align macOS permissive Seatbelt profiles with deny-default model by @ompatel-aiml in https://github.com/google-gemini/gemini-cli/pull/28424
* fix(core): mitigate infinite ReAct loops and prompt injection loops by @amelidev in https://github.com/google-gemini/gemini-cli/pull/28429
* fix(a2a-server): enforce workspace trust and task isolation to prevent RCE by @luisfelipe-alt in https://github.com/google-gemini/gemini-cli/pull/28470
* fix(core): sequentially verify cached credentials and restore GOOGLE_APPLICATION_CREDENTIALS fallback by @luisfelipe-alt in https://github.com/google-gemini/gemini-cli/pull/28472
* feat(evals): add eval coverage report command by @ved015 in https://github.com/google-gemini/gemini-cli/pull/28169


**Full Changelog**: https://github.com/google-gemini/gemini-cli/compare/v0.52.0...v0.53.0