azure-horizondb

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves technical documentation from official Microsoft domains (learn.microsoft.com). These are recognized as trusted and well-known services for documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for external content.
  • Ingestion points: The microsoft_docs_fetch and fetch_webpage tools are used to retrieve documentation from the web (found in SKILL.md).
  • Boundary markers: No specific delimiters or safety warnings for the fetched content are defined in the skill instructions.
  • Capability inventory: The skill does not have capabilities for file modification, command execution, or network data transmission.
  • Sanitization: No explicit sanitization or verification of the retrieved markdown is performed by the skill.
  • [SAFE]: No malicious patterns such as obfuscation, privilege escalation, or persistence were detected. The behavior is consistent with the skill's stated purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 12:23 AM