notion-meeting-intelligence
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates a workflow where untrusted data is retrieved from external sources and used to perform subsequent actions, creating an attack surface for indirect prompt injection.
- Ingestion points: Data is ingested from the Notion workspace via the
Notion:notion-fetchandNotion:notion-searchtools in the workflow described inSKILL.md. - Boundary markers: The instructions do not define delimiters or clear boundaries to isolate the retrieved content from the agent's instructions, nor is the agent instructed to ignore commands embedded in the fetched data.
- Capability inventory: The skill uses
Notion:notion-create-pagesandNotion:notion-update-pageto write data back to Notion based on the processed inputs. - Sanitization: There is no explicit sanitization or validation of the fetched content before it is processed and written to new documents.
Audit Metadata