notion-local-dev-loop
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a development workflow that retrieves data from the Notion API (e.g., users, database queries, and page content), which represents a surface for indirect prompt injection if the external data contains malicious instructions.
- Ingestion points: Data is ingested via
notion.users.listandnotion.databases.queryinreferences/examples.mdandreferences/testing.md. - Boundary markers: The provided code snippets do not implement specific boundary markers or "ignore" instructions for the data retrieved from Notion.
- Capability inventory: The skill allows use of
Bash(npm:*)andBash(pnpm:*), as well as fileReadandWriteoperations. - Sanitization: No explicit sanitization, validation, or filtering of retrieved Notion content is demonstrated in the implementation examples.
Audit Metadata