notion-spec-to-implementation
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted data from external Notion specification pages to generate project artifacts.\n
- Ingestion points: Data enters the agent context through the
Notion:notion-fetchtool as described inSKILL.md(Step 1) andreference/spec-parsing.md.\n - Boundary markers: The templates provided in
reference/standard-implementation-plan.mdandreference/task-creation-template.mddo not include explicit delimiters or system-level instructions to ignore embedded agent commands within the parsed specification text.\n - Capability inventory: The skill possesses significant write capabilities within the user's Notion environment via
Notion:notion-create-pagesandNotion:notion-update-pagetools, which are used to generate plans and tasks based on parsed requirements as defined inSKILL.mdandreference/task-creation.md.\n - Sanitization: There is no evidence of content sanitization or validation logic to filter out steering instructions or non-requirement content from the source specifications before they are used to generate plan descriptions or task acceptance criteria.
Audit Metadata