AI agents invoke install to trigger actions in Lint. 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.
'Install' actions run external processes to install packages or dependencies, which constitutes executing an external operation. The description 'Runs' confirms execution behavior. Severity is medium because installing packages can introduce malicious dependencies or alter system state, but it is reversible and not directly destructive. Confidence is reduced due to the truncated description.
From the tool's definition Tool name is 'install' on a server with tools like ansible-playbook, bazel, audit, add-package — suggesting package/dependency installation execution. Description is truncated ('Runs') and uninformative beyond confirming it executes something.
Documented attack patterns abuse exactly the kind of access install gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Lint, and nothing reaches the server without passing your rules. This is the rule we recommend for install:
{
"version": "1",
"default": "deny",
"tools": {
"install": {
"limits": [
{
"counter": "install_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}install 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.
Runs. It is categorised as a Execute tool in the Lint MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Lint MCP server in PolicyLayer and add a rule for install: 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 Lint. Nothing to install.
install 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 install 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 install. 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.
install is provided by the Lint MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Lint, 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.
202 Lint tools catalogued and risk-classified — across an index of 43,000+ MCP servers.