The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted project data, creating a surface for instructions embedded in that data to influence agent behavior.
Ingestion points: The agent reads project files, level scripts, and code using the read_file and search_code tools as described in the suggested process and security guardrails in SKILL.md.
Boundary markers: Absent. The skill instructions do not require the agent to use delimiters or explicit instructions to ignore embedded commands within the files it processes.
Capability inventory: The skill has access to high-impact tools including execute_command, write_file, create_file, edit_file, and run_build.
Sanitization: Absent. There are no instructions for sanitizing, escaping, or validating the content of the files before the agent acts upon the information they contain.

manage-scene-lifecycle