AI agents invoke install_package to trigger actions in PSKit. 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 packages executes external processes, modifies system state by adding software, and can introduce malicious code or alter system behavior. It is not purely a write operation because it runs executables and scripts from external sources. The blast radius is high since a misused package install could compromise the entire system.
From the tool's definition Install a package using the detected or specified package manager
Attacks that exploit this kind of access
Install a package using the detected or specified package manager. It is categorised as a Execute tool in the PSKit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PSKit MCP server in PolicyLayer and add a rule for install_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 PSKit. Nothing to install.
install_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_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_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_package is provided by the PSKit MCP server (nickalus12/pskit). 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 →