List all registered hooks Use when native Bash hooks (via Claude Code\
AI agents call hooks_list 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 retrieves and displays existing hook registrations without modifying, executing, or deleting anything. It is a purely informational query operation. The blast radius of misuse is minimal—an agent could only learn what hooks exist in the system, which is non-destructive read access.
From the tool's definition The tool name is 'hooks_list' and the description states 'List all registered hooks'. The verb 'List' and the action of retrieving/querying hook metadata indicates data retrieval with no side effects.
Attacks that exploit this kind of access
List all registered hooks Use when native Bash hooks (via Claude Code\. 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 hooks_list: 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.
hooks_list 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 hooks_list 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 hooks_list. 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.
hooks_list 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.