Detect worker triggers from user prompt (for UserPromptSubmit hook) Use when native Bash hooks (via Claude Code\
AI agents call hooks_worker-detect 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 tool appears to detect/identify worker triggers from a prompt input, which is a read/analysis operation. However, its output may be used to spawn or trigger workers (via 'UserPromptSubmit hook'), meaning misuse could indirectly cause higher-severity downstream actions. The description is incomplete (truncated), which reduces confidence.
From the tool's definition 'Detect worker triggers from user prompt' - the tool analyzes/reads a user prompt to identify triggers, suggesting a read/analysis operation with no direct side effects
Attacks that exploit this kind of access
Detect worker triggers from user prompt (for UserPromptSubmit hook) 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_worker-detect: 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_worker-detect 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_worker-detect 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_worker-detect. 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_worker-detect 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.