The Agent Skills Directory

Prompt Injection (LOW): The skill is designed to ingest and process data from external, potentially untrusted sources like documentation and source code repositories, which creates a surface for indirect prompt injection.
Ingestion points: External data enters the agent context through tools such as search_docs, get_doc_page, search_code_semantic, search_code_text, and get_card as defined in SKILL.md.
Boundary markers: No specific boundary markers, XML tags, or 'ignore embedded instructions' delimiters are used to wrap the retrieved content in the provided examples.
Capability inventory: The skill provides significant capabilities including file reading (read_file) and project management actions (update_card_field, spawn_cards, move_card_to_stage) across multiple boards.
Sanitization: There is no evidence of content sanitization or validation performed on the retrieved data before it is presented to the model.

adynato-aimake