Scan code for security vulnerabilities
AI agents call scan-code 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.
This tool performs static analysis or scanning to detect vulnerabilities—a non-destructive inspection activity with no side effects on the scanned code or system state. It retrieves and analyzes information but does not create, modify, delete, or execute code. The blast radius of misuse is minimal since scanning cannot alter system state or data.
From the tool's definition Tool name 'scan-code' and description 'Scan code for security vulnerabilities' indicates a read-only analysis operation that examines code without modifying it.
Attacks that exploit this kind of access
Scan code for security vulnerabilities. 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 scan-code: 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.
scan-code 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 scan-code 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 scan-code. 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.
scan-code 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.