The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the dxs CLI tool and jq for fetching, validating, and updating platform configurations.
Evidence: Shell commands such as dxs configuration upsert, dxs configuration get, and jq .json are used in SKILL.md for standard development lifecycle tasks.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and processing data from other agent skills.
Ingestion points: Requirements briefs from the requirements-gathering skill and schema metadata from the schema-explorer skill as described in SKILL.md.
Boundary markers: No specific delimiters or boundary markers are defined in the instructions to separate untrusted data from instructions.
Capability inventory: The skill has the capability to execute shell commands and modify configuration files via the dxs CLI.
Sanitization: The skill does not implement explicit sanitization or escaping logic for external content before using it to generate configurations.

selector-creator