Saved command templates on a node. Save reusable snippets with {{var}} placeholders, then run them with variable substitution.
AI agents invoke omniwire_snippet to trigger actions in OmniWire. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes arbitrary command templates across distributed infrastructure nodes via persistent SSH connections. Misuse allows an AI agent to run malicious commands, access unauthorized resources, or disrupt system operations. The variable substitution mechanism could be exploited for injection attacks.
From the tool's definition Tool runs saved command templates with variable substitution ('run them with variable substitution'). Combined with server description stating it 'executes commands...across multiple nodes', this is code/command execution.
Documented attack patterns abuse exactly the kind of access omniwire_snippet gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OmniWire, and nothing reaches the server without passing your rules. This is the rule we recommend for omniwire_snippet:
{
"version": "1",
"default": "deny",
"tools": {
"omniwire_snippet": {
"limits": [
{
"counter": "omniwire_snippet_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}omniwire_snippet stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Saved command templates on a node. Save reusable snippets with {{var}} placeholders, then run them with variable substitution. It is categorised as a Execute tool in the OmniWire MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OmniWire MCP server in PolicyLayer and add a rule for omniwire_snippet: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches OmniWire. Nothing to install.
omniwire_snippet is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the omniwire_snippet rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for omniwire_snippet. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
omniwire_snippet is provided by the OmniWire MCP server (voidchecksum/omniwire). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OmniWire, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
88 OmniWire tools catalogued and risk-classified — across an index of 43,000+ MCP servers.