AI agents use konsulto_set_active_audit to create or update resources in Konsulto — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Konsulto environment.
This tool performs a reversible state modification—changing which audit is pinned/active in the current session. It does not delete, execute code, move funds, or trigger external operations. While it affects session context (potentially influencing which audit subsequent tools operate on), the action itself is a Write operation.
From the tool's definition The tool description states it will 'Pin one audit as the session', which modifies session state by setting an active audit context. This is a write operation that changes which audit is currently active.
Attacks that exploit this kind of access
Pin one audit as the session\. It is categorised as a Write tool in the Konsulto MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Konsulto MCP server in PolicyLayer and add a rule for konsulto_set_active_audit: 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 Konsulto. Nothing to install.
konsulto_set_active_audit is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the konsulto_set_active_audit 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 konsulto_set_active_audit. 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.
konsulto_set_active_audit is provided by the Konsulto MCP server (konsulto/konsulto-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →