AI agents call pbs_list_snapshots to retrieve information from Homelab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays backup snapshot metadata (timestamps, sizes) across datastores without performing any write, deletion, or execution operations. It is a pure read/query operation with no side effects. Severity is low because listing snapshots poses minimal risk even if misused by an agent, though access to backup inventory could inform further attacks.
From the tool's definition Tool description states it "List[s] recent backup snapshots" - a query operation that retrieves information with no modification or deletion of data.
Attacks that exploit this kind of access
List recent backup snapshots across all PBS datastores with timestamps and sizes. It is categorised as a Read tool in the Homelab MCP Server, which means it retrieves data without modifying state.
Register the Homelab MCP server in PolicyLayer and add a rule for pbs_list_snapshots: 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 Homelab. Nothing to install.
pbs_list_snapshots 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 pbs_list_snapshots 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 pbs_list_snapshots. 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.
pbs_list_snapshots is provided by the Homelab MCP server (nainounen/homelab-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 →