The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes common CLI tools including curl, mkdir, and cat to perform API operations and manage configuration, which is appropriate for its function. \n- [DATA_EXFILTRATION]: Authentication tokens are retrieved from a local configuration file (~/.config/notion/api_key) and sent to the official Notion domain (api.notion.com). As this is a well-known service, the operation is considered safe under established rules. \n- [PROMPT_INJECTION]: Static analysis identifies a surface for indirect prompt injection as the skill ingests data from the Notion API (ingestion points in SKILL.md) without boundary markers or sanitization. However, no malicious intent was detected. \n- [SAFE]: No obfuscation, remote code execution, or hardcoded credentials were detected. The skill's operations are transparent and consistent with its documentation.

notion