The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill provides installation commands in references/setup.md that download and pipe scripts directly to a shell for execution (curl ... | bash and irm ... | iex). These resources are hosted on the official GitHub repository for Epic Games (https://raw.githubusercontent.com/EpicGames/lore/main/scripts/install.sh).
[INDIRECT_PROMPT_INJECTION]: The skill documents functionality for interacting with external repositories, which presents a surface for indirect prompt injection.
Ingestion points: Commands like lore clone, lore sync, and lore branch merge (described in references/cli.md and references/workflow.md) read content and metadata from remote repository partitions.
Boundary markers: The instructions do not define specific delimiters or warnings to prevent the agent from following instructions embedded in the repository data.
Capability inventory: The skill provides access to file system writes, network requests, and authentication token management.
Sanitization: There are no documented procedures for sanitizing external content before it is processed by the agent.

lore