azure-personalizer

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves documentation from official Microsoft Learn domains (learn.microsoft.com). These references are used to provide the agent with up-to-date technical context and troubleshooting guidance.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it ingests data from external web pages. However, the risk is mitigated by the use of highly trusted official documentation sources.
  • Ingestion points: External URLs listed in the Category Index within SKILL.md.
  • Boundary markers: Absent; fetched content is not wrapped in specific delimiters.
  • Capability inventory: The skill is designed to perform network fetches via fetch_webpage and mcp_microsoftdocs:microsoft_docs_fetch tools.
  • Sanitization: No explicit sanitization or validation of the remote documentation content is defined in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 07:54 AM