azure-bastion
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 from official Microsoft domains (learn.microsoft.com). These resources are well-known and trusted, and the skill documents these connections neutrally.
- [INDIRECT_PROMPT_INJECTION]: The skill processes content fetched from remote documentation URLs, which constitutes an indirect prompt injection surface.
- Ingestion points: Documentation fetch operations referenced in SKILL.md.
- Boundary markers: Not explicitly defined in the skill instructions.
- Capability inventory: The skill uses
read_file,fetch_webpage, andmcp_microsoftdocs:microsoft_docs_fetchtools. - Sanitization: No explicit sanitization or filtering of the fetched documentation content is described.
Audit Metadata