向 Gemini 当前输入框上传图片（仅上传，不发送消息），可配合 gemini_send_message 组合使用
AI agents use gemini_upload_images to create or update resources in Gemini Skill — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gemini Skill environment.
This tool uploads (writes) image files to a chat interface input box. It is a reversible operation that modifies the UI state but does not execute irreversible deletion, trigger external code execution with arbitrary side effects, or involve financial transactions. It fits the Write category (creates/modifies data reversibly).
From the tool's definition Tool description states "向 Gemini 当前输入框上传图片（仅上传，不发送消息）" (upload images to Gemini's current input box, upload only, do not send message).
Documented attack patterns abuse exactly the kind of access gemini_upload_images gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gemini Skill, and nothing reaches the server without passing your rules. This is the rule we recommend for gemini_upload_images:
{
"version": "1",
"default": "deny",
"tools": {
"gemini_upload_images": {
"limits": [
{
"counter": "gemini_upload_images_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}gemini_upload_images stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
向 Gemini 当前输入框上传图片（仅上传，不发送消息），可配合 gemini_send_message 组合使用. It is categorised as a Write tool in the Gemini Skill MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gemini Skill MCP server in PolicyLayer and add a rule for gemini_upload_images: 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 Gemini Skill. Nothing to install.
gemini_upload_images is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the gemini_upload_images 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 gemini_upload_images. 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.
gemini_upload_images is provided by the Gemini Skill MCP server (wjz-p/gemini-skill). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 Gemini Skill tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 Gemini Skill tools catalogued and risk-classified — across an index of 42,500+ MCP servers.