列出所有任务
AI agents call list_all_tasks to retrieve information from Auto Video Generator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries task data with no side effects. It fits the Read category as it provides visibility into tasks without performing any operations that would change state, execute code, or affect system resources. The low severity reflects the minimal blast radius—an AI agent listing tasks cannot cause direct harm, though information disclosure risks are minimal in this context.
From the tool's definition Tool name 'list_all_tasks' and description '列出所有任务' (list all tasks) indicate a retrieval operation that queries existing tasks without modifying, deleting, or executing any of them.
Attacks that exploit this kind of access
列出所有任务. It is categorised as a Read tool in the Auto Video Generator MCP Server, which means it retrieves data without modifying state.
Register the Auto Video Generator MCP server in PolicyLayer and add a rule for list_all_tasks: 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 Auto Video Generator. Nothing to install.
list_all_tasks 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 list_all_tasks 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 list_all_tasks. 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.
list_all_tasks is provided by the Auto Video Generator MCP server (zgmurder/auto_video_generator-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →