azure-servicebus-ts

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • Category 4: Unverifiable Dependencies & Remote Code Execution (LOW): The skill installs @azure/service-bus and @azure/identity. These packages belong to the 'azure' organization, which is a trusted source. According to the [TRUST-SCOPE-RULE], this finding is downgraded to LOW.\n- Category 8: Indirect Prompt Injection (LOW): The skill handles untrusted data from Azure Service Bus messages.\n
  • Ingestion points: Untrusted data enters the agent context via receiver.receiveMessages and receiver.subscribe in SKILL.md and references/queues-topics.md.\n
  • Boundary markers: Absent; the code examples do not demonstrate the use of delimiters or 'ignore' instructions when processing message bodies.\n
  • Capability inventory: The skill allows for full message lifecycle management (sending, receiving, settling, and dead-lettering).\n
  • Sanitization: Absent; the message content is logged and processed directly in the examples without sanitization, providing a surface where an agent might be influenced by instructions embedded in a message.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 03:34 AM