The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl to interact with Elasticsearch and Kibana security APIs for user, role, and role mapping management. This is the primary and expected function of the skill.
[PROMPT_INJECTION]: The skill features a natural language decomposition workflow that translates user requests into security configurations, presenting a surface for indirect prompt injection.
Ingestion points: Natural language access requests processed in SKILL.md.
Boundary markers: Not present.
Capability inventory: Administrative API access via curl as defined in SKILL.md and references/api-reference.md.
Sanitization: The skill provides guidance for generating strong passwords but does not specify sanitization for other user-controlled strings like role names or query filters.

elasticsearch-authz