The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by ingesting untrusted data from external Notion sources.
Ingestion points: Data enters the agent's context through tools like NOTION_FETCH_BLOCK_CONTENTS, NOTION_QUERY_DATABASE, NOTION_FETCH_COMMENTS, and NOTION_LIST_USERS (SKILL.md).
Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the ingested data.
Capability inventory: The skill possesses extensive write and administrative capabilities, including creating and updating pages, inserting database rows, replacing page content, and modifying database schemas (SKILL.md).
Sanitization: There are no mentioned mechanisms for sanitizing or validating content retrieved from Notion before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server endpoint and references documentation from a well-known service.
The setup instructions require adding https://rube.app/mcp as a remote MCP server in the client configuration.
The skill references documentation and toolkits provided by Composio at https://composio.dev/toolkits/notion.

notion-automation