AI agents call check_updates to retrieve information from Cachyos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and reports information about available updates. It performs read-only queries to pacman/AUR package databases with no side effects, modifications, or execution of changes. The severity is low because even if misused by an agent, checking for updates cannot damage the system or cause unwanted state changes.
From the tool's definition Tool checks for pending updates using 'checkupdates' and 'paru -Qua' commands, which query package managers for available updates without modifying system state.
Attacks that exploit this kind of access
Pending updates from repos (checkupdates) and AUR (paru -Qua). It is categorised as a Read tool in the Cachyos MCP Server, which means it retrieves data without modifying state.
Register the Cachyos MCP server in PolicyLayer and add a rule for check_updates: 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 Cachyos. Nothing to install.
check_updates 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 check_updates 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_updates. 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_updates is provided by the Cachyos MCP server (raindancer118/cachyos-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 →