The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's operational rules in AGENTS.md instruct the agent to execute the compose-agentsmd tool via the shell to manage and update project rules.
[DYNAMIC_EXECUTION]: The skill utilizes compose-agentsmd to dynamically regenerate the AGENTS.md file at the start of a session, ensuring the agent operates with the most current guidelines.
[EXTERNAL_DOWNLOADS]: The skill uses npx or npm to fetch and run the compose-agentsmd package from the official npm registry, which is a well-known and trusted service.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze user-supplied GUI designs and task flows, which constitutes a potential attack surface for indirect prompt injection.
Ingestion points: GUI design mockups, descriptions of interactive components, and screenshots provided by the user (as described in SKILL.md and README.md).
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings for user input are present in the provided instructions.
Capability inventory: The agent has the capability to execute shell commands via compose-agentsmd for rule maintenance.
Sanitization: The instructions do not specify any validation or sanitization routines for the processed GUI design data.

guided-gui-design