AI agents invoke package-clean to trigger actions in Github. 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.
This tool executes a build system command (Swift package cleaning) which triggers external operations with side effects on the filesystem. While not destructive in the sense of deleting source code, it removes build artifacts and modifies system state, making it Execute rather than Read. The medium severity reflects that misuse could interfere with development workflows but is typically reversible by rebuilding.
From the tool's definition Cleans Swift package build artifacts - performs build system operations that execute cleanup commands and modify the local build directory state.
Attacks that exploit this kind of access
Cleans Swift package build artifacts and returns structured result. It is categorised as a Execute tool in the Github MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Github MCP server in PolicyLayer and add a rule for package-clean: 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 Github. Nothing to install.
package-clean 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 package-clean 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 package-clean. 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.
package-clean is provided by the Github MCP server (@paretools/github). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.