The Agent Skills Directory

[DATA_EXPOSURE]: The skill instructions involve reading an API key from a local configuration file at ~/.config/notion/api_key. This is consistent with standard credential management for CLI tools and does not constitute unauthorized exposure.
[COMMAND_EXECUTION]: The skill utilizes common shell commands such as curl, cat, and mkdir to interact with the Notion API. These operations are scoped to the skill's primary function and target the official Notion domain (api.notion.com).
[INDIRECT_PROMPT_INJECTION]: The skill interacts with external data by retrieving content from Notion pages and databases. This creates a surface for indirect prompt injection if the retrieved content contains instructions designed to influence the agent's behavior. Ingestion points: Notion API responses (SKILL.md). Boundary markers: None present. Capability inventory: curl (network access) and cat (file system access). Sanitization: None specified.

better-notion