Install a named dependency using the bundled installer script.
AI agents invoke install_dependency to trigger actions in Android Reverse Engineering. 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 executes an installer script to install software dependencies on the host system. Running installer scripts constitutes code/command execution with potentially broad system-level effects. Misuse could result in installation of malicious or unintended packages, making this a high-severity Execute action.
From the tool's definition Install a named dependency using the bundled installer script
Documented attack patterns abuse exactly the kind of access install_dependency gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Android Reverse Engineering, and nothing reaches the server without passing your rules. This is the rule we recommend for install_dependency:
{
"version": "1",
"default": "deny",
"tools": {
"install_dependency": {
"limits": [
{
"counter": "install_dependency_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}install_dependency 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.
Install a named dependency using the bundled installer script. It is categorised as a Execute tool in the Android Reverse Engineering MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Android Reverse Engineering MCP server in PolicyLayer and add a rule for install_dependency: 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 Android Reverse Engineering. Nothing to install.
install_dependency 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_dependency 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_dependency. 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_dependency is provided by the Android Reverse Engineering MCP server (vichhka-git/android-reverse-engineering-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Android Reverse Engineering, 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.
6 Android Reverse Engineering tools catalogued and risk-classified — across an index of 43,000+ MCP servers.