Suggest reviewers for git diff changes Use when native
AI agents call analyze_diff-reviewers 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 is a Read operation: it queries/analyzes existing git diff data and retrieves reviewer recommendations without modifying any state. Severity is medium rather than low because the tool accesses code change information which could reveal sensitive implementation details, business logic, or security patterns if misused by an agent to profile repository contents.
From the tool's definition Tool name 'analyze_diff' and description 'Suggest reviewers for git diff changes' indicate the tool examines git diffs (code changes) and returns reviewer suggestions based on analysis.
Attacks that exploit this kind of access
Suggest reviewers for git diff changes Use when native. 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 analyze_diff-reviewers: 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.
analyze_diff-reviewers 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 analyze_diff-reviewers 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 analyze_diff-reviewers. 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.
analyze_diff-reviewers 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.