developmental-coach-notion
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes session data from Notion, which creates a surface for indirect prompt injection where malicious instructions in notes could influence agent behavior.
- Ingestion points: Historical coaching data is loaded from Notion via
notion-searchandnotion-fetchinSKILL.md. - Boundary markers: The instructions do not define specific delimiters or 'ignore' instructions for the retrieved data.
- Capability inventory: The skill has permissions to create and update Notion pages and databases using
notion-create-pages,notion-update-page, andnotion-create-databaseinSKILL.md. - Sanitization: No content validation or sanitization is performed on the retrieved data.
Audit Metadata