Supply chain and agent configuration
This category groups related risk explanations. A finding is a reason to review the activity and its context, not proof that a breach occurred.
Risk types
Section titled “Risk types”- Tool name shadowing
An MCP tool uses a name that matches a familiar built-in tool.
- New or changed MCP server use
An MCP server is used for the first time, or its recorded connection changes.
- Plugin and registry configuration changes
A command or saved configuration contains patterns for installing plugins, adding MCP servers, or changing package registries.
- Risky dependency sources and install patterns
A call uses a package source or install pattern that deserves a closer look.
- Agent hook configuration access
A call refers to Claude Code settings and includes hook-related text.
- MCP configuration changes and redirection
A call touches user-level MCP settings or contains a command that writes agent configuration.
- Workspace instruction and MCP configuration access
A tool call explicitly refers to CLAUDE.md or .mcp.json.
- Listed collection and testing domains
A tool call reaches a host on the rule domain list, or writes a URL for one into a script or configuration file.
Event categories
Section titled “Event categories”These event category values map to this library category: supply_chain. Use the rule index to find the explanation for a specific rule ID.