Prts Sandbox
v1.0.0Isolated Kali Linux sandbox for running pentest tools and risky commands safely.
⭐ 0· 216·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The skill's name/description promise an 'Isolated Kali Linux' sandbox, but the package contains only a wrapper script that calls a hardcoded API (http://protocol-spaces-api:3000). No sandbox runtime, container images, or install steps are provided. A real sandbox would normally include the container image, an installer, or clear instructions to deploy the sandbox service; this mismatch means the skill relies on an opaque external service to actually run commands.
Instruction Scope
SKILL.md instructs the agent (and users) to run the included script which sends arbitrary commands to the /execute endpoint of the Protocol Spaces API. That means user-supplied commands and their outputs are transmitted over HTTP to an external service the skill does not ship or document. The instructions do not require verifying that the service is local/trusted, and they encourage sending sensitive or risky commands there, creating a risk of unintended disclosure or remote execution.
Install Mechanism
There is no install spec (instruction-only) and nothing is written to disk by an installer, which reduces some risk. However, the skill assumes an external service is available at a hardcoded hostname. The lack of an install mechanism for that service is a usability and trust issue: the caller must already have the API running from an unknown source.
Credentials
The skill requests no credentials or env vars, yet it transmits arbitrary commands and receives outputs from the Protocol Spaces API over plain HTTP. Absence of declared credentials may be disingenuous: the script implicitly trusts a network service and could expose sensitive command contents or results to whatever resolves that hostname. The hardcoded API URL and use of HTTP (not HTTPS) are disproportionate for a sandbox claimed to protect the host.
Persistence & Privilege
The skill is not 'always: true' and does not request elevated agent/system privileges or modify other skills. It is user-invocable and allows autonomous invocation by default (normal for skills).
What to consider before installing
This skill does not itself provide the sandbox — it is a client that forwards whatever commands you run to an external service at http://protocol-spaces-api:3000. Before installing or using: 1) Confirm where 'protocol-spaces-api' comes from and that you trust and control it (preferably host it locally). 2) Do not send sensitive commands or credentials to this skill unless the API is verified and on a trusted local network; the script uses plain HTTP. 3) Prefer a skill that ships the sandbox runtime or provides reproducible install instructions for the sandbox service. 4) If you must use this, ensure the hostname resolves to localhost or an isolated network (e.g., via /etc/hosts) and inspect or run the API service source code yourself to ensure it doesn't exfiltrate data. If you cannot verify the API, treat the skill as untrusted.Like a lobster shell, security has layers — review code before you run it.
latestvk973sv0hjb54tmvwvv9j29gng582f7h6
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🛡️ Clawdis
Binsbash, curl, jq