The Agent Skills Directory

Command Line Interaction: The skill provides instructions for users to configure the environment using the codex CLI and npx. Specifically, it suggests commands to add an MCP server and enable features like rmcp_client. These are standard administrative tasks for setting up the required environment.
External Resource Integration: The skill references and downloads tools from Linear's official infrastructure (mcp.linear.app). While these involve remote code execution patterns through npx -y mcp-remote, they are directed at a well-known service and are part of the intended setup process for the integration.
Indirect Prompt Injection Surface: The skill is designed to read and process issues, comments, and documentation from a Linear workspace. This creates a potential surface where malicious instructions embedded in issue descriptions could influence the agent's behavior.
Ingestion points: Data enters the context via tools like list_issues, get_issue, and search_documentation (SKILL.md).
Boundary markers: The instructions do not explicitly define delimiters for external data.
Capability inventory: The skill can create or update issues and comments, and execute shell commands for setup.
Sanitization: There is no explicit mention of sanitizing or escaping the content retrieved from Linear before processing.

linear