notion-research-documentation
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses official Notion MCP tools to search and fetch content. Setup instructions point exclusively to official Notion infrastructure (mcp.notion.com), which is a trusted service for this vendor's tools.- [SAFE]: The documentation provides high-quality guidance on data synthesis and citation, emphasizing the use of Notion's native mention-page tags to maintain a clear chain of evidence back to source material.- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests untrusted data from Notion and uses it to generate new documentation. However, this is inherent to its primary purpose and is managed by structured templates.
- Ingestion points: Notion:notion-fetch as described in SKILL.md.
- Boundary markers: Absent; research is synthesized directly into templates.
- Capability inventory: Notion:notion-create-pages and Notion:notion-update-page in SKILL.md.
- Sanitization: Absent; the agent relies on its internal reasoning to synthesize content.- [SAFE]: No obfuscation, hardcoded credentials, or unauthorized command execution patterns were found in the skill body, metadata, or referenced guides.
Audit Metadata