The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external command outputs (organization names, member emails, etc.) which could theoretically contain malicious instructions designed to influence the agent's behavior.
Ingestion points: The agent ingests and processes the JSON output from mcloud organizations list and mcloud organizations get as described in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the ingested data are present in the skill instructions.
Capability inventory: The skill utilizes Bash to execute mcloud and jq commands, providing a mechanism to act on processed data.
Sanitization: There is no evidence of sanitization, filtering, or validation of the fields retrieved from the cloud service before they are processed by the agent.

mcloud-organizations