# Posts by tag 'prompt injection' — Liran Tal

AI security researcher, open-source maintainer, and author. Explore Liran Tal’s blog, research papers, developer tools, books, and conference talks.

Canonical: https://lirantal.com/tag/prompt-injection

*   Jul 17, 2026 · 12 min read

    ## [Invisible Unicode Can Hijack Gemini CLI Agent Skills](/blog/gemini-cli-invisible-unicode-skill-injection)

    I disclosed a Gemini CLI prompt injection where invisible Unicode tag characters in SKILL.md caused the agent to run a hidden command. Google closed the report as out of scope because the workspace was trusted and YOLO mode was enabled.

    *   [security](/tag/security)
    *   [ai agents](/tag/ai-agents)
    *   [gemini cli](/tag/gemini-cli)
    *   [prompt injection](/tag/prompt-injection)
    *   [unicode](/tag/unicode)

     [![](/_astro/gemini-cli-invisible-unicode-skill-injection.AW0ivLkB_Z2nFK4g.png)](/blog/gemini-cli-invisible-unicode-skill-injection)

*   May 9, 2026 · 16 min read

    ## [Is Prompt Injection an Unsolvable Problem in AI?](/blog/is-prompt-injection-unsolvable-problem-ai)

    Prompt injection is not a bug you patch but an architectural limit baked into how LLMs process language. This post traces the problem from Gödel and Hofstadter to modern jailbreaks, agent skill supply chains, and why defenders must shift from elimination to survivability.

    *   [security](/tag/security)
    *   [ai](/tag/ai)
    *   [prompt injection](/tag/prompt-injection)
    *   [llm](/tag/llm)
    *   [ai agents](/tag/ai-agents)

     [![](/_astro/is-prompt-injection-unsolvable-problem-ai.CNHPYK7E_1xccHK.png)](/blog/is-prompt-injection-unsolvable-problem-ai)