The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted content from the knowledge base (markdown files), which creates an attack surface for indirect prompt injection.
Ingestion points: All .md files located within the knowledge base directory structure.
Boundary markers: None defined for the ingestion of file content.
Capability inventory: Read, Write, Glob, Grep, and Bash tools are available to the agent.
Sanitization: No explicit sanitization or validation of the ingested markdown content is performed before processing.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to interact with the aiwg command-line interface for path resolution and storage configuration management.
Evidence: Execution of aiwg kb path and other aiwg subcommands to determine the knowledge base root and list entities.

kb-health