The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external CLI tool outputs, which presents a surface for potential indirect prompt injection.
Ingestion points: Diagnostic and status data is retrieved from commands like matrix instance info, gh auth status, and codex login status in SKILL.md.
Boundary markers: The instructions do not define specific delimiters to isolate tool outputs or direct the agent to ignore instructions within that data.
Capability inventory: The skill has the ability to execute shell commands and manage terminal sessions via run_command and terminal-related tools.
Sanitization: There is no defined process for validating or sanitizing the output received from the executed commands.
[COMMAND_EXECUTION]: The skill directs the execution of several CLI tools, such as matrix, codex, claude, and gh, to facilitate the setup and authentication of the cloud environment. These actions are standard for the skill's intended administrative use case.
[EXTERNAL_DOWNLOADS]: The skill refers to matrix-os.com for technical documentation and app.matrix-os.com for instance management. These links represent legitimate vendor-owned resources for the Matrix OS platform.

matrix-onboarding