The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill implements microservice templates that ingest untrusted data which is subsequently used in network and messaging operations, creating a surface for indirect prompt injection attacks.\n
Ingestion points: The order_data parameters in APIGateway.create_order and OrderService.create_order within SKILL.md.\n
Boundary markers: The templates do not demonstrate the use of delimiters or specific instructions to ignore embedded prompts in the data.\n
Capability inventory: The code examples utilize httpx.AsyncClient for internal service calls and AIOKafkaProducer for event distribution.\n
Sanitization: No input validation, filtering, or sanitization logic is implemented in the provided architectural snippets.

microservices-patterns