AI agents invoke system_update to trigger actions in Cachyos. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Running a full system upgrade modifies potentially hundreds of packages system-wide. While technically a Write/Execute operation, it carries critical blast radius: a bad upgrade can break system boot, destabilize running services, introduce incompatible dependencies, or render the system unbootable. It executes privileged package manager commands with broad, hard-to-reverse system-wide effects.
From the tool's definition 'Upgrade the system (pacman -Syu, or paru -Syu with AUR)' — triggers a full system upgrade across all packages
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
[ACTION] Upgrade the system (pacman -Syu, or paru -Syu with AUR). It is categorised as a Execute tool in the Cachyos MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cachyos MCP server in PolicyLayer and add a rule for system_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 Cachyos. Nothing to install.
system_update is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the system_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 system_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.
system_update 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 →