Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add itallstartedwithaidea/agent-skills --skill sandbox-hardeninggit clone --depth 1 https://github.com/itallstartedwithaidea/agent-skillsWrote 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/itallstartedwithaidea/agent-skills/sandbox-hardening)<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/sandbox-hardening"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/sandbox-hardening/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/itallstartedwithaidea/agent-skills/sandbox-hardening"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/sandbox-hardening.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 | $0.00026 | $0.01486 |
| Opus 5 | $0.00013 | $0.00743 |
| Sonnet 5 | $0.00005 | $0.00297 |
| Haiku 4.5 | $0.00003 | $0.00149 |
Grade C, and why
sandbox-hardening scanned grade C with 4 findings 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 7d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
"curl | sh", "wget | bash", "chmod 777", Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
"curl | sh", "wget | bash", "chmod 777", Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"rm -rf /", "mkfs", "dd if=", "> /dev/sd", Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
"curl | sh", "wget | bash", "chmod 777", 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.
Sandbox Hardening
Part of Agent Skills™ by googleadsagent.ai™
Description
Sandbox Hardening isolates agent execution environments using container sandboxing, permission boundaries, resource limits, and network segmentation. The agent configures and validates sandboxes that prevent AI-generated code from accessing unauthorized resources, consuming unbounded compute, or affecting the host system.
An AI agent with unrestricted shell access is a security liability. Without sandboxing, a prompt injection or hallucinated command could delete files, exfiltrate data, install malware, or consume unbounded resources. Sandbox Hardening applies the principle of least privilege: the agent receives only the permissions it needs, in an isolated environment with strict resource limits and monitored network access.
This skill covers three isolation levels: process-level sandboxing (seccomp, AppArmor), container-level isolation (Docker with restricted capabilities), and VM-level isolation (microVMs like Firecracker). The appropriate level depends on the trust boundary: internal development tools use process-level, multi-tenant platforms use container-level, and untrusted code execution requires VM-level isolation.
Use When
- Running AI-generated code in production or shared environments
- Configuring agent execution environments with least-privilege access
- Deploying multi-tenant AI platforms where users share infrastructure
- Executing untrusted code from user inputs or AI outputs
- Implementing compliance requirements for isolated execution
- Building sandboxed development environments for agents
How It Works
graph TD
A[Agent Task] --> B{Trust Level Assessment}
B -->|Internal Dev| C[Process Sandbox]
B -->|Multi-Tenant| D[Container Sandbox]
B -->|Untrusted Code| E[VM Sandbox]
C --> F[seccomp + AppArmor Profile]
D --> G[Docker: No Root + Read-Only FS]
E --> H[Firecracker microVM]
F --> I[Resource Limits: CPU, Memory, Disk]
G --> I
H --> I
I --> J[Network Policy: Allowlist Only]
J --> K[Filesystem: Scoped Mount]
K --> L[Monitoring: Syscall Audit]
L --> M[Execution within Sandbox]
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.
- 7d ago First seen · 170 lines · 26 tokens per session scan C fedb3ee62184
sandbox-hardening is a skill published in the GitHub repository itallstartedwithaidea/agent-skills (37 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 1,486 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 4 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
atmos-helmfile
Helmfile orchestration: sync/apply/destroy/diff, Kubernetes deployments, varfile generation, EKS integration, source management.
atmos-devcontainer
Devcontainer orchestration: start/stop/attach/shell/exec/rebuild, instance management, config handling, VS Code integration.
atmos-container
Atmos container components: components.container, Docker Compose migration, build/run/push/pull/up/down/list/ps/logs/exec, stack-scoped persistent containers, container workflow steps, compositions, and hooks.
atmos-emulator
Atmos emulator components: local AWS/GCP/Azure/Kubernetes/Vault/OpenBao/registry emulators, components.emulator, !emulator, identities, persistence, health checks, and emulator commands.
detecting-cryptomining-in-cloud
This skill teaches security teams how to detect and respond to unauthorized cryptocurrency mining operations in cloud environments. It covers identifying cryptomining indicators through compute usage anomalies, network traffic patterns to mining pools, GuardDuty CryptoCurrency findings, and runtime process monitoring…
securing-azure-with-microsoft-defender
This skill instructs security practitioners on deploying Microsoft Defender for Cloud as a cloud-native application protection platform for Azure, multi-cloud, and hybrid environments. It covers enabling Defender plans for servers, containers, storage, and databases, configuring security recommendations, managing…