拉起应用（挂起态）并附加，可选在恢复前注入脚本。 Args: - package_name: 应用包名 - initial_script: 可选注入的 Frida JS 代码字符串 - script_file_path: 可选注入的 JS 文件绝对路径（优先于 initial_script） - output_file: 可选的本地电脑文件路径，用于保存 hook 输出（非安卓设备路径） Returns: - {status, pid, package, script_loaded, message}
AI agents invoke spawn to trigger actions in Frida. 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 launches an Android application, attaches a dynamic instrumentation framework (Frida) to it, and can inject arbitrary JS scripts into the process. This constitutes code execution within another process, which is a significant operation with a large blast radius — it can intercept, modify, or exfiltrate data from any running app. The most severe applicable category is Execute.
From the tool's definition 拉起应用（挂起态）并附加，可选在恢复前注入脚本 — spawns an application, attaches Frida to it, and optionally injects arbitrary JavaScript code before resuming
Documented attack patterns abuse exactly the kind of access spawn gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Frida, and nothing reaches the server without passing your rules. This is the rule we recommend for spawn:
{
"version": "1",
"default": "deny",
"tools": {
"spawn": {
"limits": [
{
"counter": "spawn_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}spawn 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.
拉起应用（挂起态）并附加，可选在恢复前注入脚本。 Args: - package_name: 应用包名 - initial_script: 可选注入的 Frida JS 代码字符串 - script_file_path: 可选注入的 JS 文件绝对路径（优先于 initial_script） - output_file: 可选的本地电脑文件路径，用于保存 hook 输出（非安卓设备路径） Returns: - {status, pid, package, script_loaded, message}. It is categorised as a Execute tool in the Frida MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Frida MCP server in PolicyLayer and add a rule for spawn: 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 Frida. Nothing to install.
spawn 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 spawn 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 spawn. 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.
spawn is provided by the Frida MCP server (zhizhuodemao/frida-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Frida tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 Frida tools catalogued and risk-classified — across an index of 42,500+ MCP servers.