WRITE/AUDIT. Evaluates one task-scoped access request and appends an allow or deny record. Requires an action, resource, and reason. Denial wins over allowance; untrusted high-risk actions and configured boundaries require approval. Fails closed if auditing fails.
AI agents use check_task_access to create or update resources in Agentic Task System — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agentic Task System environment.
The tool writes an access control record (allow or deny) to an audit log. While it reads/evaluates an access request, its primary side effect is appending a persistent record that governs future access decisions. Misuse could grant or deny access inappropriately, affecting security boundaries — hence high severity. It does not delete data or execute code, placing it in Write rather than Destructive or Execute.
From the tool's definition WRITE/AUDIT. Evaluates one task-scoped access request and appends an allow or deny record. Fails closed if auditing fails.
Attacks that exploit this kind of access
WRITE/AUDIT. Evaluates one task-scoped access request and appends an allow or deny record. Requires an action, resource, and reason. Denial wins over allowance; untrusted high-risk actions and configured boundaries require approval. Fails closed if auditing fails. It is categorised as a Write tool in the Agentic Task System MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agentic Task System MCP server in PolicyLayer and add a rule for check_task_access: 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 Agentic Task System. Nothing to install.
check_task_access 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 check_task_access 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 check_task_access. 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.
check_task_access is provided by the Agentic Task System MCP server (renezander030/agentic-task-system). 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 →