notion
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill instructs users to store their Notion API key in a local configuration file at
~/.config/notion/api_key. This key is subsequently read and used to authenticate requests to the official Notion API (api.notion.com). This is a standard and expected credential management practice for API-integrated skills. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, creating a potential surface for indirect prompt injection.
- Ingestion points: Reads page content and database entries through the Notion API (e.g.,
GET /v1/blocks/{page_id}/childrenandPOST /v1/data_sources/{id}/queryinSKILL.md). - Boundary markers: None identified in the provided instructions; the agent processes the retrieved content directly.
- Capability inventory: The skill uses
curlto interact with the Notion API and perform file system operations likemkdir,echo, andcatfor configuration management (SKILL.md). - Sanitization: No explicit sanitization or validation of the content retrieved from the Notion API is described.
Audit Metadata