Skills
skills/founderjourney/claude-skills/notion-mastery/Gen Agent Trust Hub

notion-mastery

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill processes data from external sources (Apollo.io, Notion) without explicit sanitization, creating a surface for indirect injection.
  • Ingestion points: references/n8n-workflows.md (Apollo API responses and Notion database fields).
  • Boundary markers: Absent in instructions and templates.
  • Capability inventory: references/n8n-workflows.md utilizes n8n_execute_workflow and n8n_create_workflow via the n8n-mcp.
  • Sanitization: None present in the provided JavaScript logic or workflow templates.
  • Dynamic Execution (LOW): The skill generates and executes logic (JavaScript and n8n workflow definitions) at runtime based on user requirements.
  • Evidence: references/n8n-workflows.md contains code snippets and instructions for the agent to create and execute workflows.
  • Context: This is the primary purpose of the skill, so the severity is reduced per the assessment framework.
  • Data Exposure & Credentials (SAFE): The skill follows best practice by using placeholders for API keys.
  • Evidence: NOTION_API_KEY=secret_xxx and APOLLO_API_KEY=xxx are defined as environment variables in references/n8n-workflows.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:34 PM