AI agents call which_package_owns 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 performs a passive lookup in the package database to return information about file ownership. It has no side effects, does not modify any data, and does not execute arbitrary commands. It is a straightforward information retrieval operation, consistent with the 'Read' category for queries and lookups.
From the tool's definition Tool description states it queries which installed package owns a file using 'pacman -Qo', which is a read-only query operation that retrieves ownership information without modifying system state.
Attacks that exploit this kind of access
Which installed package owns a file (pacman -Qo). 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 which_package_owns: 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.
which_package_owns 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 which_package_owns 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 which_package_owns. 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.
which_package_owns 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 →