The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill operates on subscriber data that can be influenced by external actors and possesses destructive capabilities.
Ingestion points: The KIT_LIST_SUBSCRIBERS tool (SKILL.md) retrieves external data such as email addresses and metadata.
Boundary markers: The skill lacks explicit instructions or delimiters to ensure the agent ignores potential commands embedded within the retrieved data.
Capability inventory: The skill includes high-impact destructive tools including KIT_DELETE_SUBSCRIBER and KIT_DELETE_BROADCAST (SKILL.md).
Sanitization: No sanitization or validation logic is defined to filter malicious content from the subscriber data before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The setup instructions direct the user to add an external MCP server endpoint (https://rube.app/mcp) to their client configuration to enable the toolkit's functionality.

convertkit-automation