brevo-automation

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs users to add an external MCP server endpoint (https://rube.app/mcp) to their client configuration. This service provides the logic and execution environment for the tools used to interact with Brevo.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it ingests untrusted data from an external platform and possesses tools capable of modifying that platform's state.
  • Ingestion points: The tools BREVO_LIST_EMAIL_CAMPAIGNS and BREVO_GET_ALL_EMAIL_TEMPLATES retrieve content from the Brevo account which may contain instructions intended to manipulate the agent.
  • Boundary markers: Absent. The instructions do not define delimiters or provide specific guidance for the agent to treat data from these tools as potentially untrusted content.
  • Capability inventory: The skill includes powerful write-access tools such as BREVO_UPDATE_EMAIL_CAMPAIGN, BREVO_CREATE_OR_UPDATE_EMAIL_TEMPLATE, and BREVO_DELETE_EMAIL_TEMPLATE which could be abused if the agent is successfully injected.
  • Sanitization: Absent. There is no requirement or logic provided for the agent to sanitize or validate the content retrieved from Brevo before it is used in subsequent operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 06:43 PM