The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes instructions to use the system shell to install the llama-index library and its associated integrations via pip.
[EXTERNAL_DOWNLOADS]: The installation steps involve downloading official packages from the Python Package Index (PyPI). These are standard dependencies for the LlamaIndex framework.
[PROMPT_INJECTION]: The skill documents the creation of systems that ingest untrusted data from various sources, which constitutes a surface for indirect prompt injection.
Ingestion points: Data is ingested via SimpleDirectoryReader (local file system), SimpleWebPageReader (external URLs), and DatabaseReader (database queries) in SKILL.md.
Boundary markers: The provided examples do not explicitly demonstrate the use of prompt delimiters or instructions to ignore embedded commands within the processed data.
Capability inventory: The skill facilitates file system access, network requests (web reading), and database connectivity to build knowledge bases.
Sanitization: No specific content sanitization, validation, or filtering of external data is demonstrated in the basic configuration examples.

llamaindex