get_attack_chains

What get_attack_chains does on Pentest Ai

AI agents call get_attack_chains to retrieve information from Pentest Ai without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why get_attack_chains is rated Low

This tool performs information retrieval only. It presents attack chain data that has already been discovered during a pentest engagement, allowing review of compromise paths. There are no side effects, no code execution, no data modification or deletion. The blast radius of misuse is minimal—worst case an authorized user sees attack chain information they already have access to. Classified as Read with low severity.

From the tool's definition Tool retrieves and displays already-discovered attack chains without modifying, executing, or deleting any data. The description states 'Get discovered attack chains' and 'Shows how... findings chain together' — clear read operations that query results.

The rule that runs get_attack_chains safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Pentest Ai, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_attack_chains, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_attack_chains": {}
  }
}

Questions about get_attack_chains