azure-messaging-webpubsubservice-py
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- Indirect Prompt Injection Surface: The skill allows an agent to listen for messages via WebSocket listeners, such as
on("server-message")andon("group-message")inSKILL.md. This represents a potential surface for indirect prompt injection because the incoming data is untrusted. - Ingestion points: Untrusted data enters the agent context through WebSocket event listeners defined in
SKILL.md. - Boundary markers: The provided code samples do not include specific delimiters or instructions to mitigate the risk of an agent acting on content embedded in messages.
- Capability inventory: The skill provides capabilities for broad messaging and group management in
SKILL.md, which could be misused if an injection occurs. - Sanitization: There is no evidence of content sanitization or validation in the provided examples.
- Official Package Installation: The skill recommends the installation of
azure-messaging-webpubsubserviceandazure-messaging-webpubsubclient. These are official Microsoft SDKs for interacting with Azure services and are considered safe resources.
Audit Metadata