The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from environment variables which could potentially contain untrusted content if modified by external actors.
Ingestion points: Data enters the context through mcloud variables list and mcloud variables get command outputs as described in SKILL.md.
Boundary markers: The skill instructs the agent to use --json output, providing a structured format for data processing.
Capability inventory: Tool access is strictly limited to mcloud and jq bash commands defined in the YAML frontmatter.
Sanitization: The skill utilizes jq for parsing and selecting specific data fields from the command output.

mcloud-variables