The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data which presents a surface for indirect prompt injection. * Ingestion points: Data is retrieved from the Make API via the MAKE_GET_OPERATIONS tool. * Boundary markers: The instructions do not define specific delimiters or safety prompts to isolate external data from the agent's instructions. * Capability inventory: The skill has the capability to perform network operations and manage connections through the rube MCP toolkit. * Sanitization: No sanitization or validation of the retrieved Make scenario metadata is specified in the instructions.
[SAFE]: The skill references well-known services for its primary functionality and follows standard authentication workflows.

make-automation