AI agents use article_update to create or update resources in Voog — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Voog environment.
This tool creates or modifies data reversibly by updating article fields. It is not destructive (does not delete), not financial, not executable code. The incomplete description ('go to') suggests field mapping but does not alter the classification. Severity is medium because unintended article updates could impact published content, SEO, or user-facing pages, but changes can typically be reverted.
From the tool's definition Tool name 'article_update' and description 'Update an existing article. Title/body/excerpt go to' explicitly indicate modification of article data (title, body, excerpt fields).
Attacks that exploit this kind of access
Update an existing article. Title/body/excerpt go to. It is categorised as a Write tool in the Voog MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Voog MCP server in PolicyLayer and add a rule for article_update: 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 Voog. Nothing to install.
article_update 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 article_update 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 article_update. 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.
article_update is provided by the Voog MCP server (runnel/voog-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 →