AI agents call gemini_get_images to retrieve information from Gemini Skill without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a query operation that retrieves metadata about images already present in a Gemini session. It explicitly does not download or modify data, only returns metadata information about existing resources. This is a read-only operation with no capability to modify, delete, or execute code. The blast radius of misuse is minimal—an attacker could only discover what images are visible in the session.
From the tool's definition Tool description states '获取当前 Gemini 会话中所有已加载的图片列表（不下载，仅返回元信息）' which translates to 'retrieve all loaded images in current Gemini session (not downloading, only returning metadata)'. The tool retrieves and lists image metadata without side effects.
Documented attack patterns abuse exactly the kind of access gemini_get_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_get_images:
{
"version": "1",
"default": "deny",
"tools": {
"gemini_get_images": {}
}
}gemini_get_images is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
获取当前 Gemini 会话中所有已加载的图片列表（不下载，仅返回元信息）. It is categorised as a Read tool in the Gemini Skill MCP Server, which means it retrieves data without modifying state.
Register the Gemini Skill MCP server in PolicyLayer and add a rule for gemini_get_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_get_images is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the gemini_get_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_get_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_get_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.