Get a WASM agent\
AI agents call wasm_agent_files to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The verb 'Get' and lack of any modification, deletion, or execution language suggests this is a data retrieval operation. WASM agents are typically accessed as static artifacts. No side effects, destructive operations, or external code execution are indicated. Classified as Read with low severity due to minimal blast radius if misused by an AI agent—it would only retrieve existing agent data.
From the tool's definition Tool name 'wasm_agent_files' with description 'Get a WASM agent' indicates retrieval of file/agent data without modification or execution.
Attacks that exploit this kind of access
Get a WASM agent\. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for wasm_agent_files: 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 Claude Flow. Nothing to install.
wasm_agent_files 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 wasm_agent_files 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 wasm_agent_files. 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.
wasm_agent_files is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.