brevo-automation
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the retrieval and processing of data from external Brevo API endpoints, including campaign lists and email templates. This content is untrusted and could potentially contain instructions aimed at influencing the agent's behavior.
- Ingestion points: Data enters the agent's context through tools such as
BREVO_LIST_EMAIL_CAMPAIGNS,BREVO_GET_ALL_EMAIL_TEMPLATES, andBREVO_GET_ALL_SENDERSinSKILL.md. - Boundary markers: The instructions do not include specific delimiters or guidelines for the agent to ignore instructions that might be embedded in the retrieved content.
- Capability inventory: The agent has permissions to read, create, update, and delete email campaigns and templates via the Brevo toolkit.
- Sanitization: No explicit sanitization or validation of the content fetched from Brevo is described in the skill instructions.
Audit Metadata