AI agents call hooks_pre-edit to retrieve information from Ruflo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool's described purpose is to fetch context and agent suggestions before an edit occurs, which is a read/query operation. It does not perform the edit itself. However, the description is incomplete (truncated at 'Claude Code\'), slightly lowering confidence. Severity is medium because in an agentic swarm context, pre-edit hooks could influence downstream autonomous editing behavior.
From the tool's definition "Get context and agent suggestions before editing a file" — retrieves context and suggestions prior to an edit action
Attacks that exploit this kind of access
Get context and agent suggestions before editing a file Use when native Bash hooks (via Claude Code\. It is categorised as a Read tool in the Ruflo MCP Server, which means it retrieves data without modifying state.
Register the Ruflo MCP server in PolicyLayer and add a rule for hooks_pre-edit: 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 Ruflo. Nothing to install.
hooks_pre-edit 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_pre-edit 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_pre-edit. 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_pre-edit is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
hooks_pre-edit is one line of Ruflo's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →