Incident · Feb 2026 · Prompt injection

Cline

The title of a GitHub issue carried instructions for an AI triage bot. The bot followed them, an npm token was stolen, and a rogue release went out to developers for about eight hours.

What happened

The title of a GitHub issue carried instructions for an AI triage bot. The bot followed them, an npm token was stolen, and a rogue release went out to developers for about eight hours.

Source: Cline post-mortem ↗. Follow it for the full account.

The cause: prompt injection

Text the assistant reads (an email, a web page, a file name) carries instructions, and the assistant follows them as if they came from you.

Framework entries that cover it: OWASP LLM01: Prompt Injection · MITRE ATLAS: LLM Prompt Injection

The solution
  1. 1

    What would have caught this one

    Treating every field an agent reads as hostile: titles, comments, file names, commit messages.

  2. 2

    Prevent the whole class

    Treat everything the assistant reads as untrusted. Separate reading from acting, and require confirmation before any action that sends data out.

  3. 3

    Test for it

    Plant instructions in every field the assistant can read, including encoded and split ones, and check whether any action or data leaves.