azure-messaging-webpubsub-java

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides documentation for the official Microsoft Azure library com.azure:azure-messaging-webpubsub. These dependencies originate from a trusted organization.
  • [SAFE]: Sensitive configuration values such as connection strings and access keys are handled using standard placeholders (<connection-string>, <access-key>) in the documentation, preventing the exposure of real credentials.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides functions to broadcast data to multiple clients via WebSockets. While this is the intended purpose of the SDK, it represents a surface where untrusted data could be transmitted to client applications.
  • Ingestion points: Messaging methods in SKILL.md such as sendToAll, sendToGroup, and sendToUser which accept arbitrary message content.
  • Boundary markers: Not present in the generic documentation examples.
  • Capability inventory: Network transmission of messages via the Azure Web PubSub service; management of client connections and groups.
  • Sanitization: Not shown in the provided code snippets; the skill assumes the developer will handle sanitization of data before broadcasting.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 06:19 PM