notion

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to read or accept a Notion API key (from env or user paste) and then include that secret verbatim in Authorization headers and curl command args, which forces the LLM to emit secret values in its outputs.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). In this Notion skill, runtime reads are performed only by the agent issuing first-party Notion API calls (e.g., GET https://api.notion.com/v1/pages/{page_id} and GET https://api.notion.com/v1/blocks/{page_id}/children, plus POST /v1/search), but the workflow description does not expose any required step that ingests arbitrary outsider-authored free text without first selecting specific items.