notion-spec-to-implementation
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources (Notion pages) to perform its core functions.
- Ingestion points: Content is retrieved using the
Notion:notion-fetchtool as described inSKILL.mdandreference/spec-parsing.mdto analyze requirements. - Boundary markers: The instructions do not define clear delimiters or specify that the agent should ignore instructions embedded within the fetched specification text.
- Capability inventory: The agent has permissions to search, read, create, and modify pages and databases within the Notion workspace (
Notion:notion-search,Notion:notion-fetch,Notion:notion-create-pages,Notion:notion-update-page). - Sanitization: The workflow does not include explicit validation or sanitization of the fetched text before using it to generate implementation plans or individual tasks.
Audit Metadata