The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads the layero CLI tool from the npm registry using npx to ensure the most recent version is utilized for deployment tasks.\n- [REMOTE_CODE_EXECUTION]: The agent connects to a remote Model Context Protocol (MCP) server at https://mcp.layero.ru/mcp to access project management and monitoring tools.\n- [COMMAND_EXECUTION]: The skill performs various operations by executing shell commands, including project initialization, deployment, and environment management.\n- [DATA_EXFILTRATION]: Project files and directory contents are uploaded to the vendor's infrastructure as part of the standard deployment process.\n- [INDIRECT_PROMPT_INJECTION]: The skill's design involves reading and processing external data, which introduces a potential vector for indirect prompt injection.\n
Ingestion points: The skill reads layero.json and .layero/project.json files from the local environment, parses real-time build logs from the platform, and retrieves site content via the read_site tool.\n
Boundary markers: The instructions do not define specific delimiters or instructions to prevent the agent from following directions potentially embedded in these external data sources.\n
Capability inventory: The skill allows for shell command execution, network requests, and file system modifications.\n
Sanitization: There are no documented procedures for validating or sanitizing the data ingested from project files or build logs.

layero