workflow-builder

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configuration specifies the installation of official MCP servers (@makenotion/mcp-server and @modelcontextprotocol/server-slack) via npx. These are recognized packages from trusted and well-known organizations in the MCP ecosystem.
  • [DATA_EXFILTRATION]: Pseudo-code examples include a webhook URL https://api.yourautomation.com/trigger. This is a placeholder domain used to illustrate standard business automation workflows where Notion events trigger external actions. No suspicious data exfiltration was detected.
  • [CREDENTIALS_UNSAFE]: The skill correctly uses environment variables (${NOTION_API_KEY}, ${SLACK_BOT_TOKEN}) for credential management in the server configuration, adhering to security best practices.
  • [PROMPT_INJECTION]: The skill is designed to process business data from Notion and Slack. While processing external data always introduces a theoretical surface for indirect prompt injection, this skill does not contain instructions that would make it particularly vulnerable, such as unsafe interpolation of untrusted strings into system-level commands.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 11:21 PM
Security Audit — agent-trust-hub — workflow-builder