brevo-automation

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to add an external MCP server endpoint at https://rube.app/mcp to access the required Brevo tools.
  • [COMMAND_EXECUTION]: The skill utilizes a set of tools (e.g., BREVO_UPDATE_EMAIL_CAMPAIGN, BREVO_CREATE_OR_UPDATE_EMAIL_TEMPLATE) to execute operations on the Brevo platform.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it retrieves and processes content from external campaigns and templates. * Ingestion points: Untrusted data from campaign lists and template definitions enter the agent context through BREVO_LIST_EMAIL_CAMPAIGNS and BREVO_GET_ALL_EMAIL_TEMPLATES. * Boundary markers: The skill does not implement delimiters or 'ignore' instructions for the data retrieved from Brevo. * Capability inventory: The skill has the capability to write to the Brevo API, including updating campaign contents. * Sanitization: No sanitization or validation of the retrieved HTML or text content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 07:55 AM