The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves analyzing external and local repositories, creating a surface for indirect prompt injection where instructions embedded in the analyzed code could influence the agent.
Ingestion points: The /builder:reverse-engineer [repo-path] command in SKILL.md allows the agent to ingest content from both local file paths and remote repository URLs.
Boundary markers: There are no specific boundary markers or instructions provided to the agent to distinguish between its system instructions and the data found within the analyzed files.
Capability inventory: The agent is empowered to scan repository structures, extract design patterns, and generate new files including SKILL.md files, agent blueprints, and UV scripts.
Sanitization: The skill does not define any sanitization or validation logic for the content read from external repositories before it is processed by the agent.
[COMMAND_EXECUTION]: The skill defines several orchestration commands such as /builder:reverse-engineer, /builder:workflow-designer, and /builder:generate-script. These commands direct the agent to perform file system operations and repository analysis as part of its intended workflow automation role.
[EXTERNAL_DOWNLOADS]: The skill includes instructions for the agent to analyze remote GitHub repositories, which involves downloading content from external URLs to the local environment for processing.

builder-workflow