NYC

brevo-automation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [No Code] (SAFE): The skill consists entirely of markdown documentation and tool definitions. No scripts, binaries, or executable files are included in the skill package.
  • [Indirect Prompt Injection] (LOW): The skill is designed to retrieve and process content from external email campaigns and templates, which serves as a potential attack surface.
  • Ingestion points: Data enters the agent context via BREVO_LIST_EMAIL_CAMPAIGNS and BREVO_GET_ALL_EMAIL_TEMPLATES which pull live content from Brevo accounts.
  • Boundary markers: The provided instructions do not specify any delimiters (e.g., XML tags or triple quotes) to separate retrieved campaign data from agent instructions.
  • Capability inventory: The agent has the capability to perform write actions, such as creating or updating email campaigns and templates, which could be abused if the agent follows instructions hidden within a retrieved email.
  • Sanitization: No content sanitization or validation steps are mentioned in the workflow for processing external data.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:05 PM