nby-notion-smart-categorize
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill manages a Notion API token by instructing the agent to store it in a local .env file. This follows secure development practices for managing secrets and avoids hardcoding credentials.\n- [SAFE]: The skill performs network operations to api.notion.com and r.jina.ai. These are well-known services necessary for the skill's operation, and no sensitive local data is exfiltrated to these domains.\n- [DYNAMIC_EXECUTION]: Static Python code is used via python3 -c to parse JSON data from API responses. This is a standard method for data extraction within the skill's execution environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data, creating a potential surface for indirect prompt injection.\n
- Ingestion points: Notion page titles and content retrieved via the Notion API, and web content fetched through r.jina.ai.\n
- Boundary markers: None present; the skill does not wrap external content in delimiters.\n
- Capability inventory: The skill uses curl and WebFetch for network access, python3 for data processing, and Write for configuration.\n
- Sanitization: No explicit sanitization of external content is performed before categorization.
Audit Metadata