azure-signalr-service
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches technical documentation and reference material from official Microsoft domains (learn.microsoft.com). These references target well-known, trusted service infrastructure.
- [INDIRECT_PROMPT_INJECTION]: The skill has a theoretical attack surface for indirect prompt injection through external data ingestion.
- Ingestion points: The skill retrieves content from external URLs specified in
SKILL.mdusing retrieval tools likemicrosoft_docs_fetch. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the fetched content are defined in the skill instructions.
- Capability inventory: The skill does not define local script execution, system writes, or network exfiltration capabilities; it serves as a knowledge reference.
- Sanitization: No specific sanitization or filtering logic is applied to the retrieved documentation content before it is processed by the agent.
Audit Metadata