The Agent Skills Directory

[DATA_EXFILTRATION]: The skill defines and accesses a sensitive local file path ~/.config/notion/api_key to store and retrieve the Notion API key. This key is subsequently used in the Authorization header for network requests to Notion's API.
[COMMAND_EXECUTION]: The skill relies on shell command execution via curl to perform all API operations, including reading and writing data to Notion's servers.
[PROMPT_INJECTION]: The skill ingests data from external Notion pages and databases, creating a surface for indirect prompt injection where malicious instructions embedded in Notion content could influence agent behavior.
Ingestion points: Fetches page content and block children through GET requests to api.notion.com/v1/blocks/{page_id}/children in SKILL.md.
Boundary markers: No delimiters or safety instructions are present to distinguish between retrieved Notion content and system instructions.
Capability inventory: The skill uses curl to execute network requests (read/write) and uses cat to read local configuration files.
Sanitization: There is no evidence of filtering, escaping, or validation of the data retrieved from the Notion API before it is processed by the agent.

notion