notion-research-documentation
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and synthesize untrusted data from a Notion workspace via the
Notion:notion-searchandNotion:notion-fetchtools. This introduces a potential surface for indirect prompt injection where instructions embedded in Notion pages could influence the agent's behavior during synthesis or documentation creation. - Ingestion points: Content is retrieved from Notion pages in
SKILL.md(Workflow Step 1) and processed in Step 3. - Boundary markers: The skill encourages the use of structured templates and formal citations (
reference/citations.md), which provide some context separation, but no explicit "ignore embedded instructions" delimiters are enforced. - Capability inventory: The skill has the ability to write back to the workspace using
Notion:notion-create-pagesandNotion:notion-update-pageacross all synthesis workflows. - Sanitization: There are no mentioned mechanisms for filtering or sanitizing the content retrieved from Notion before it is processed by the agent.
Audit Metadata