Shield Agent AI

All replays

Vendor replays

Coding agent risks with Docker: replays and fixes

2 replays involve Docker: 0 reported incidents and 2 command classes. Each one shows the call, a fix that needs no extra tool, and what KYA did in the replay.

  • docker volume prune with all and force

    Fix: Back up the data in named volumes to a place outside Docker. Do not let the agent use a Docker daemon that holds volumes you cannot rebuild, because access to the Docker socket is access to every volume.

    Replay result: Stopped.

  • Read the Docker registry credentials file

    Fix: Use a Docker credential helper (credsStore in ~/.docker/config.json, such as osxkeychain), so the file holds no password, and add a deny rule such as Read(~/.docker/**) to the Claude Code settings. A Read rule also covers shell commands such as cat, but not a script that opens the file itself, so enable the Claude Code sandbox when the block must hold.

    Replay result: Stopped.

All replays

Does a client ask how you control AI coding agents?

The Answer Pack drafts your answers to the AI section of a client security questionnaire.

Get the Answer Pack