Gemini CLI v0.61.0 ships indirect prompt injection fix and sandbox hardening
gemini-cli-robot · ghdev · 2026-09-24
google-gemini/gemini-cli released v0.61.0. Notable security fixes:
- Prevent indirect prompt injection via build file modifications and untrusted flags
- Harden sandbox filesystem boundaries and isolate runtime state
- Preserve explicit versioned Flash model IDs
- Fix AgentLoopContext property loss across object spread
Users running agent workflows on Gemini CLI should upgrade.
More from coding & agent
- Why inference speed will be AI products' biggest competitive edge in 1–2 years — itsOmSarraf_ · 2026-11-11
- What happened when I moved vector retrieval into Snowflake SQL instead of orchestrating RAG outside — dima806_dima · 2026-11-11
- OpenAI engineer runs Codex for 26 days straight hunting Atlantis, spawning "vibe archaeology" — Polymarket · 2026-11-11
- He replaced a $5,000/month ghostwriter with 11 Claude Skills and earned $47,000 from one post — aryanXmahajan · 2026-11-11
- Refero Styles ships 2,000+ DESIGN.md files to give Claude Code real design taste — bbssppllvv · 2026-11-11
- Agent circuit breaker: openclaw shorts bot halts itself after 3 failed experiments — Rich_Standard_1724 · 2026-11-11