AI agents call fabric_cve_queue to retrieve information from Git Steer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries CVE queue entries with optional filtering parameters. It has no side effects—it does not execute code, modify data, delete entries, or trigger external operations. It purely returns information about existing CVE records, making it a Read operation. The blast radius if misused is minimal since an agent can only view CVE information already known to the system.
From the tool's definition Tool name contains 'list' operation (fabric_cve_queue) and description explicitly states 'List CVE queue entries filtered by status and severity.' The verb 'list' combined with 'filtered by' indicates a retrieval operation with no modification or execution of…
Attacks that exploit this kind of access
[git-fabric] List CVE queue entries filtered by status and severity. It is categorised as a Read tool in the Git Steer MCP Server, which means it retrieves data without modifying state.
Register the Git Steer MCP server in PolicyLayer and add a rule for fabric_cve_queue: 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 Git Steer. Nothing to install.
fabric_cve_queue is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the fabric_cve_queue 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 fabric_cve_queue. 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.
fabric_cve_queue is provided by the Git Steer MCP server (ry-ops/git-steer). 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 →