notion-research-documentation

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill performs expected research tasks using standard Notion API tools with no evidence of unauthorized operations or data exfiltration.
  • [EXTERNAL_DOWNLOADS]: The skill configuration points to the official Notion MCP server (https://mcp.notion.com/mcp), which is a trusted and well-known service required for the skill's functionality.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from Notion pages (Ingestion points: Notion:notion-fetch in SKILL.md) and possesses the capability to write to the workspace (Capability inventory: Notion:notion-create-pages, Notion:notion-update-page). It lacks explicit separation between instructions and fetched data (Boundary markers: Absent) and does not specify sanitization (Sanitization: Absent), creating a theoretical surface for indirect prompt injection that is inherent to research-oriented agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 08:24 PM