notion-spec-to-implementation
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests data from external Notion pages, which creates a surface for indirect prompt injection. This is a characteristic of the skill's intended functionality for parsing specifications.\n
- Ingestion points: Notion page content is retrieved using
Notion:notion-fetchinSKILL.mdandreference/spec-parsing.md.\n - Boundary markers: The workflow does not explicitly define delimiters or warnings to ignore instructions embedded within the fetched specification content.\n
- Capability inventory: The skill includes tools to search, create, and update Notion pages and databases (
Notion:notion-search,Notion:notion-create-pages,Notion:notion-update-page).\n - Sanitization: No automated sanitization or escaping of the ingested content is specified.\n- [SAFE]: The skill's configuration and network references target
mcp.notion.com, which is the official domain for a well-known service.\n- [SAFE]: The skill follows standard best practices for the Codex platform, including instructions for OAuth-based login and local environment configuration.
Audit Metadata