notion-spec-to-implementation
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Processing of Untrusted Content: The skill is designed to fetch and interpret documentation from Notion pages, which constitutes an indirect prompt injection surface. Content within these pages could theoretically be crafted to influence the agent's behavior during the parsing and planning phases.
- Ingestion points: Content is retrieved using the
Notion:fetchtool as described inSKILL.mdandreference/spec-parsing.md. - Boundary markers: While the workflow instructs the agent to focus on specific sections (e.g., 'Requirements', 'Acceptance Criteria'), there are no explicit delimiters or 'ignore' instructions used to wrap the fetched external content to prevent the agent from following instructions embedded within the data.
- Capability inventory: The agent has the capability to write back to the workspace using
Notion:notion-create-pagesandNotion:notion-update-page, allowing it to create or modify tasks and plans based on the processed data. - Sanitization: The skill does not explicitly define sanitization or validation steps for the content extracted from the fetched pages before it is interpolated into new Notion pages.
Audit Metadata