brevo
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Brevo, such as contact details and CRM records, which creates a surface for indirect prompt injection if the agent interprets this data as instructions.
- Ingestion points: External data is ingested through various Brevo actions (e.g.,
list-contacts,get-deal) and raw API requests documented inSKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in
SKILL.md. - Capability inventory: The skill has the ability to read, create, update, and delete CRM data, and can perform arbitrary network requests through the Membrane proxy as defined in
SKILL.md. - Sanitization: There are no explicit sanitization or validation steps described for the external data in
SKILL.md. - [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/clipackage from the npm registry to enable connection management and action execution.
Audit Metadata