Gemini CLI and Claude Code Flaws Expose CI Secrets
If an AI coding agent runs in your CI on content outsiders can write (issues, PRs, comments), check versions and workflow permissions this week; laptop users on auto-update already have the fixes.
Must act: Teams running Gemini CLI or Claude Code in GitHub Actions or other CI on untrusted input, especially with pinned old versions, --yolo, or write-scoped tokens.
Can relax: Individual developers on auto-updating installs who do not feed untrusted repos or issues to the agent, and teams that run no AI agent in CI.
- Update run-gemini-cli to 0.1.22+ and Gemini CLI to 0.39.1+; check pinned versions in .github/workflows
- Update Claude Code to 2.1.163 or later (claude --version; npm i -g @anthropic-ai/claude-code@latest)
- For untrusted triggers (issues, fork PRs, comments), follow the hardening guide and do not set GEMINI_TRUST_WORKSPACE=true