Skills
skills/dykyi-roman/awesome-claude-code/create-message-broker-adapter/Gen Agent Trust Hub

create-message-broker-adapter

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill generates a DomainEventHandler in references/examples.md that derives class names from the event_type header of incoming messages, which is a potential surface for indirect prompt injection.\n
  • Ingestion points: Message headers and JSON body processed in references/examples.md.\n
  • Boundary markers: Absent; the generated logic does not include delimiters or instructions to ignore embedded commands.\n
  • Capability inventory: The infrastructure layer in references/templates.md contains code for network operations with RabbitMQ, Kafka, and SQS brokers.\n
  • Sanitization: Includes a class_exists check to ensure the derived class name is valid before instantiation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 09:58 AM