notion
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to fetch and process data from external Notion pages and databases via the
/v1/blocks/{page_id}/childrenand search endpoints. This content is untrusted and could contain malicious instructions designed to influence agent behavior. - Ingestion points: Data enters the agent context through API responses from
api.notion.com(file: SKILL.md). - Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are present.
- Capability inventory: The skill uses
curlfor network requests andcatfor file reading (file: SKILL.md). - Sanitization: No evidence of sanitization or filtering of retrieved Notion content before processing.
- [COMMAND_EXECUTION]: The provided examples use standard shell utilities (
curl,cat,echo,mkdir) to manage local credentials and perform API requests to Notion's official endpoints. These are used according to the intended purpose of the skill.
Audit Metadata