AI agents invoke install_aur_package 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.
Installing an AUR package involves fetching third-party source code, building it, and installing it system-wide. This is an Execute-level action with high severity because it runs arbitrary build scripts from the AUR in user space and installs software onto the system.
From the tool's definition 'Install an AUR package via paru (builds in user space)' — triggers a build and installation process from AUR source code
Attacks that exploit this kind of access
[ACTION] Install an AUR package via paru (builds in user space). 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 install_aur_package: 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.
install_aur_package 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 install_aur_package 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 install_aur_package. 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.
install_aur_package 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 →