azure-portal
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation content from learn.microsoft.com, which is a well-known and official service provided by Microsoft.\n- [EXTERNAL_DOWNLOADS]: The skill recommends installing the mcp_microsoftdocs tool from the official MicrosoftDocs GitHub repository, which is a trusted organization.\n- [INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection by ingesting and processing data from external websites.\n
- Ingestion points: Documentation is retrieved via fetch_webpage and microsoft_docs_fetch tools within SKILL.md.\n
- Boundary markers: There are no explicit delimiters or instructions in SKILL.md to distinguish between the skill's trusted instructions and the content of the retrieved documentation.\n
- Capability inventory: The skill enables the agent to assist with Azure Portal management tasks such as RBAC configuration, dashboard JSON templates, and mobile app protection policies.\n
- Sanitization: No sanitization or validation of the fetched remote content is specified in SKILL.md.
Audit Metadata