notion-spec-to-implementation
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes specification documents from Notion via Notion:notion-fetch. This creates an attack surface where instructions embedded in a specification page could influence the agent's behavior during implementation planning.\n
- Ingestion points: Specification pages are retrieved via Notion:notion-fetch (referenced in SKILL.md and reference/spec-parsing.md).\n
- Boundary markers: The instructions do not explicitly command the agent to treat fetched content strictly as data or to ignore embedded directives.\n
- Capability inventory: The agent can create and update pages and tasks in Notion using Notion:notion-create-pages and Notion:notion-update-page.\n
- Sanitization: No specific sanitization, filtering, or validation logic is defined for the content fetched from Notion before it is interpolated into the planning prompt.
Audit Metadata