AI agents invoke run_package_test to trigger actions in Pharo Smalltalk Interop. 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.
This tool triggers code execution within the Pharo image (test code). While tests are typically designed to be side-effect-free and read-only, they can contain arbitrary logic and potentially modify state, make network calls, or interact with external systems. The blast radius is significant if an attacker or careless agent triggers tests with malicious intent or side effects.
From the tool's definition Tool name 'run_package_test' indicates execution of test code in the Pharo Smalltalk image. Description is empty, but sibling tools (eval, eval_code) demonstrate this server executes arbitrary code in a running Smalltalk environment.
Documented attack patterns abuse exactly the kind of access run_package_test gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pharo Smalltalk Interop, and nothing reaches the server without passing your rules. This is the rule we recommend for run_package_test:
{
"version": "1",
"default": "deny",
"tools": {
"run_package_test": {
"limits": [
{
"counter": "run_package_test_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_package_test 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.
run_package_test. It is categorised as a Execute tool in the Pharo Smalltalk Interop MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pharo Smalltalk Interop MCP server in PolicyLayer and add a rule for run_package_test: 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 Pharo Smalltalk Interop. Nothing to install.
run_package_test 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 run_package_test 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 run_package_test. 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.
run_package_test is provided by the Pharo Smalltalk Interop MCP server (mumez/pharo-smalltalk-interop-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pharo Smalltalk Interop, 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.
23 Pharo Smalltalk Interop tools catalogued and risk-classified — across an index of 43,000+ MCP servers.