brevo-automation

Warn

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The setup instructions require adding https://rube.app/mcp as a remote MCP server, which introduces a dependency on third-party infrastructure.
  • [DATA_EXFILTRATION]: The skill transfers email marketing data, including campaigns and sender identities, to the Brevo API through the Rube MCP gateway.
  • [PROMPT_INJECTION]: The skill processes untrusted email content from campaigns and templates, creating an attack surface for indirect prompt injection. Ingestion points: Data is retrieved from the Brevo API via BREVO_LIST_EMAIL_CAMPAIGNS and BREVO_GET_ALL_EMAIL_TEMPLATES. Boundary markers: The skill lacks explicit markers to distinguish data from instructions. Capability inventory: The skill can perform modifications and deletions within the Brevo account. Sanitization: There is no documented sanitization of external data before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 10, 2026, 01:17 AM
Security Audit — agent-trust-hub — brevo-automation