列出所有配置的Sink规则（漏洞危险函数）。
AI agents call list_sink_rules to retrieve information from JavaSinkTracer MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves a list of existing security rules/configurations. It has no side effects, does not execute code, does not modify data, and does not delete anything. The operation is purely informational and diagnostic in nature, typical of a Read category tool.
From the tool's definition Tool name 'list_sink_rules' and description 'list all configured Sink rules (vulnerability dangerous functions)' indicate a read-only operation that retrieves or queries configuration data about sink rules without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
列出所有配置的Sink规则（漏洞危险函数）。. It is categorised as a Read tool in the JavaSinkTracer MCP MCP Server, which means it retrieves data without modifying state.
Register the JavaSinkTracer MCP server in PolicyLayer and add a rule for list_sink_rules: 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 JavaSinkTracer MCP. Nothing to install.
list_sink_rules 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_sink_rules 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_sink_rules. 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_sink_rules is provided by the JavaSinkTracer MCP server (zacarx/javasinktracer_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.