The Agent Skills Directory

[COMMAND_EXECUTION]: Uses shell commands to manage local configurations and perform network requests.
The skill uses cat to read sensitive API tokens from ~/.config/notion/api_key and curl to transmit them to the Notion API.
It provides commands to write configuration data using echo.
[EXTERNAL_DOWNLOADS]: Performs network operations to communicate with the Notion API.
Requests are directed to api.notion.com, which is a well-known service associated with the skill's primary purpose.
[PROMPT_INJECTION]: Vulnerable to indirect prompt injection through data ingested from external Notion resources.
Ingestion points: Reads page content, blocks, and database query results from the Notion API (SKILL.md).
Boundary markers: Absent. The skill does not provide instructions to the agent to treat Notion content as untrusted or to use delimiters.
Capability inventory: Uses curl for network operations and cat/echo for file system access (SKILL.md).
Sanitization: Absent. There is no logic provided to escape or validate data retrieved from Notion before it is processed by the agent.

notion