azure-communication-chat-java

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [Secure Credential Management]: The skill correctly instructs users to use environment variables like AZURE_COMMUNICATION_USER_TOKEN and the CommunicationTokenCredential class rather than hardcoding sensitive information. This aligns with recommended security practices for managing user access tokens in communication services.
  • [Trusted Dependencies]: The skill utilizes official Azure SDK packages (com.azure:azure-communication-chat), which are maintained by a trusted organization and follow standard security and maintenance protocols. The use of these verified libraries ensures that the application interacts with Azure services using vetted and secure communication channels.
  • [Indirect Prompt Injection Surface]: The skill processes external message data via methods such as listMessages() and getMessage(). This represents a potential surface for indirect prompt injection if an attacker sends messages containing instructions for the agent. Ingestion points: External data enters the agent context through chat message retrieval in SKILL.md and references/examples.md. Boundary markers: Explicit delimiters or 'ignore' instructions for embedded content are not provided in the code examples. Capability inventory: The skill includes capabilities to send messages, update message content, and manage chat threads. Sanitization: Application-level sanitization of message content is recommended when displaying or processing message contents to ensure robust data handling and prevent injection attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 03:16 PM