notion-meeting-intelligence

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Prompt Injection] (LOW): Potential surface for Indirect Prompt Injection (Category 8). \n- Ingestion points: The skill ingests untrusted data from Notion using 'notion-fetch' and 'notion-query-data-sources' (see 'examples/customer-meeting.md' and 'evaluations/status-meeting-prep.json'). \n- Boundary markers: No explicit delimiters or instructions to ignore embedded commands were found in the provided templates or workflow descriptions. \n- Capability inventory: The skill has the capability to write to the workspace using 'notion-create-pages', which could be used to propagate malicious content. \n- Sanitization: There is no evidence of sanitization or validation of the ingested Notion content before it is interpolated into prompts for generating summaries and agendas.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 09:28 AM