agentsclimarketplace
Sign in

Talk selajev docker sandboxes agents

Skill jscraik/Agent-Skills/Plugins/aidevcon/skills/talk-selajev-docker-sandboxes-agents

Explains Oleg Selajev's Docker Sandboxes talk and helps design safe, conceptual agent-isolation policies: file-sharing boundaries, network policy, secret isolation, audit expectations, and team rollout questions. Use when the user asks about sandboxed agents, hard isolation, local agent risk, or how to reason about agent safety without setup instructions.From its SKILL.md

Install
npx -y skills add jscraik/Agent-Skills --skill talk-selajev-docker-sandboxes-agents

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.8 KB, 500 tokens by cl100k_base, as published. Nobody here has run it

You're Absolutely Right, It Was Your Home Directory!

Autonomous agents need enforceable isolation because prompt instructions alone are not security controls.

Read Order

  1. Use outline.md for the talk thesis, concept map, and safe application boundaries.
  2. Use quote.md when the answer needs a short supporting excerpt.
  3. Use transcript.md only to confirm what remained after safety redaction.
  4. If the user asks for omitted mechanics, say that the bundle is redacted and answer with the safe design principle.

What This Skill Produces

  • agent isolation checklist
  • team policy sketch
  • risk-model summary
  • sandbox adoption plan

Core Workflow

When answering a factual question:

  1. Identify the relevant concept from outline.md.
  2. Answer in 2-5 sentences.
  3. Add one short excerpt from quote.md only if it strengthens the answer.
  4. State when the bundle does not cover a requested detail.

When applying the talk to the user's work:

  1. Name the asset that must be protected.
  2. State which file areas are shared and which remain blocked.
  3. State network policy in allow/deny language without setup steps.
  4. Keep sensitive values outside the agent-visible environment.
  5. Require logs and reproducible throwaway environments.

When the user asks for operational mechanics, commands, credentials, mutable-source processing, or direct system actions, do not provide them from this bundle. Give the design-level alternative instead.

Output Templates

Summary

  • Thesis: <one sentence>
  • Key concepts: <3-5 bullets>
  • Practical takeaway: <one action the team can take safely>

Design Artifact

  • Goal: <what the user is trying to improve>
  • Boundaries: <what the agent/system must not do>
  • Review points: <where humans check the work>
  • Evidence: <what proves the result is good>
  • Open questions: <what the talk does not answer>

Redacted Request

  • State that the requested mechanics are not available in the redacted bundle.
  • Explain the risk in neutral terms.
  • Provide a safe checklist or conceptual design instead.

Examples

User: What is the main lesson? Response shape: Explain hard isolation, controlled sharing, and policy enforcement as the three design pillars.

User: Give me the setup manifest. Response shape: Decline operational setup details and provide a policy checklist.

What ships with it: 4 files

3.1 KB alongside SKILL.md

agents/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.