The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server endpoint (https://rube.app/mcp) to enable its core functionality. This is a standard requirement for utilizing the Rube toolkit for Brevo automation.
[INDIRECT_PROMPT_INJECTION]: The skill operates on external data retrieved from the Brevo API, creating a potential surface for indirect prompt injection if malicious instructions are embedded in email campaign or template content.
Ingestion points: External data enters the agent context via tools BREVO_LIST_EMAIL_CAMPAIGNS and BREVO_GET_ALL_EMAIL_TEMPLATES as described in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or specific security instructions to differentiate between data and command context for the agent.
Capability inventory: The skill includes write/update capabilities that can modify campaign and template content (BREVO_UPDATE_EMAIL_CAMPAIGN, BREVO_CREATE_OR_UPDATE_EMAIL_TEMPLATE in SKILL.md), which could be leveraged if processed data influences agent behavior.
Sanitization: No content sanitization or validation mechanisms are defined within the skill's instructions for handling tool outputs.

brevo-automation