azure-notification-hubs
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves documentation from external URLs (learn.microsoft.com) which constitutes an ingestion point for untrusted data. While this theoretically allows for indirect prompt injection, the risk is mitigated by the use of a highly trusted source.
- Ingestion points: Technical documentation fetched via mcp_microsoftdocs:microsoft_docs_fetch or WebFetch (SKILL.md).
- Boundary markers: None explicitly defined to wrap external content.
- Capability inventory: The skill does not define dangerous capabilities such as file system writes, shell execution, or credential access.
- Sanitization: Not implemented within the skill body.
- [EXTERNAL_DOWNLOADS]: The skill fetches content from learn.microsoft.com, which is the official documentation portal for Microsoft Azure. This is a well-known, trusted service and aligns with the skill's primary purpose of providing expert guidance.
Audit Metadata