The Agent Skills Directory

[SAFE]: The skill is a legitimate administrative tool for Mule application development. It operates using standard workspace-aware tools (get_workspace_info and manage_run_configuration) to perform its tasks. The instructions define a safe UX flow for disambiguating user requests and applying changes to configuration objects.
[INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface where user-provided strings, such as configuration names and project names, are extracted and used as parameters for tool calls. As this functionality is the primary purpose of the skill and the operations are performed via structured tools, it is considered a safe implementation of the intended feature.
Ingestion points: User-provided configuration names and project paths collected during the interaction steps.
Boundary markers: No specific delimiters or "ignore instructions" warnings are included in the prompt templates.
Capability inventory: The skill can read workspace structures and execute run configurations, which are sensitive but necessary capabilities for the skill's purpose.
Sanitization: The instructions rely on the underlying tools to perform validation and sanitization of user-provided strings.

update-mule-run-config