The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on executing shell commands via Node.js to call a specific API wrapper script (ima_api.cjs) located in a sibling directory.
[INDIRECT_PROMPT_INJECTION]: The skill ingests content from a knowledge base and user notes, which serves as an injection surface for instructions embedded in processed data.
Ingestion points: External materials fetched via get_knowledge_list and notebook entries via export_note (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or warnings to prevent the agent from obeying instructions embedded within the ingested materials.
Capability inventory: The skill has the ability to move files (move_knowledge), rename entries (rename_note), and delete note blocks (update_note).
Sanitization: There is no mention of sanitizing or validating the content of the notes or materials before they are processed.
[DYNAMIC_EXECUTION]: The skill dynamically constructs and executes shell commands to perform its core functions, involving path computation for the ima_api.cjs script.

ybrain-organize