The Agent Skills Directory

[COMMAND_EXECUTION]: Executes shell commands via npx to perform authentication tasks and manage Notion data actions such as searching, retrieving, and updating workspace content.
[EXTERNAL_DOWNLOADS]: Fetches the @useclawlink/cli package from the NPM registry to provide the core functionality for interacting with the ClawLink service.
[INDIRECT_PROMPT_INJECTION]: The skill ingests content from Notion which could contain untrusted instructions.
Ingestion points: Data retrieved via notion_search, notion_retrieve_page, notion_retrieve_block, and notion_query_database in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard embedded commands in retrieved data.
Capability inventory: The skill has extensive write permissions, including the ability to delete blocks, update databases, and create pages.
Sanitization: No methods for filtering or sanitizing content retrieved from external Notion sources are defined in the instructions.

notion