Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cinience/alicloud-skillsnpx agentmods add skills/cinience/alicloud-skills/alicloud-acs-agent-sandboxWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cinience/alicloud-skills/alicloud-acs-agent-sandbox)<a href="https://agentmods.dev/skills/cinience/alicloud-skills/alicloud-acs-agent-sandbox"><img src="https://agentmods.dev/badge/skills/cinience/alicloud-skills/alicloud-acs-agent-sandbox/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cinience/alicloud-skills/alicloud-acs-agent-sandbox"><img src="https://agentmods.dev/badge/skills/cinience/alicloud-skills/alicloud-acs-agent-sandbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00118 | $0.02480 |
| Opus 5 | $0.00059 | $0.01240 |
| Sonnet 5 | $0.00024 | $0.00496 |
| Haiku 4.5 | $0.00012 | $0.00248 |
Grade C, and why
alicloud-acs-agent-sandbox scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Cloud metadata endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- Use a dedicated sandbox vSwitch and enterprise security group. Deny metadata service `100.100.100.200/32` and private networks except for explicitly required endpoints. How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage ACS Agent Sandbox
Operate ACS Agent Sandbox through Kubernetes custom resources and the E2B-compatible API. Treat the sandbox workload as untrusted and preserve a reproducible evidence trail under output/alicloud-acs-agent-sandbox/.
Start here
- Confirm whether the target is an ACS cluster, an ACK cluster using ACS compute, or an ACK One fleet.
- Confirm kubeconfig context, namespace, region, desired image, resource size, network boundary, and requested lifecycle action.
- Run the read-only inspection before changing an existing environment:
python3 skills/compute/acs/alicloud-acs-agent-sandbox/scripts/inspect_agent_sandbox.py \
--output output/alicloud-acs-agent-sandbox/inspection.json
- Read the reference that matches the task:
- Start from an empty account/network or release the complete stack: references/bootstrap-and-teardown.md
- Create, connect, pause, resume, checkpoint, clone, upgrade, restart, or delete: references/creation-lifecycle.md
- Manage teams, API keys, quotas, or MySQL key storage: references/tenancy-storage.md
- Mount and validate OSS or NAS storage: references/storage-mounts.md
- Configure gateway routing, TrafficPolicy, L7 egress policy, credential injection, or network expansion: references/networking-security.md
- Monitor, inspect, alert, or diagnose: references/observability-inspection.md
- Look up CRDs, phases, conditions, labels, and annotations: references/crd-reference.md
- Deploy OpenClaw or operate through ACK One: references/platform-patterns.md
- Verify currency or follow an upstream procedure: references/sources.md
- State the planned mutation and its blast radius. Obtain confirmation before delete, destructive replacement, fleet-wide policy, credential-store migration, gateway cutover, or upgrade operations.
- Apply the smallest scoped change, wait for the documented terminal condition, rerun inspection, and save sanitized outputs.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 270 B
- references/bootstrap-and-teardown.md 3.5 KB
- references/crd-reference.md 3.5 KB
- references/creation-lifecycle.md 6.1 KB
- references/networking-security.md 5.4 KB
- references/observability-inspection.md 3.7 KB
- references/platform-patterns.md 2.3 KB
- references/sources.md 5.7 KB
- references/storage-mounts.md 10 KB
- references/tenancy-storage.md 2.9 KB
- scripts/e2b_smoke_test.py 7.8 KB runs code
- scripts/inspect_agent_sandbox.py 20 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 170 lines · 118 tokens per session scan C 68f4a0c930f3
alicloud-acs-agent-sandbox is a skill published in the GitHub repository cinience/alicloud-skills (396 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 2,480 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.