The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests team descriptions and player biographies from TheSportsDB API, which acts as a surface for indirect prompt injection if the external data source contains malicious instructions.
Ingestion points: The get_team_info, search_teams, and search_players commands return descriptive text from an external API.
Boundary markers: The skill instructions do not provide delimiters or "ignore instructions" warnings to help the agent distinguish between data and embedded commands.
Capability inventory: The agent processes the natural language content returned by the API calls.
Sanitization: The skill lacks instructions for sanitizing or validating the integrity of the external content before the agent processes it.

metadata