AI agents use update_finding_status to create or update resources in Repomend — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Repomend environment.
This tool modifies the status of security findings, which is a write operation on metadata. It does not execute security scans, delete findings, or trigger financial transactions. The blast radius is medium because incorrectly updating finding statuses could suppress legitimate security alerts or cause confusion in vulnerability tracking, but the operation is reversible (status can be updated again).
From the tool's definition Tool name 'update_finding_status' and description 'Update a finding' indicate modification of existing data (finding status records) in a reversible manner.
Attacks that exploit this kind of access
Update a finding. It is categorised as a Write tool in the Repomend MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Repomend MCP server in PolicyLayer and add a rule for update_finding_status: 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 Repomend. Nothing to install.
update_finding_status 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 update_finding_status 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 update_finding_status. 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.
update_finding_status is provided by the Repomend MCP server (repomend-dev/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 →