azure-api-management
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from official Microsoft domains (learn.microsoft.com) and references code samples from the Azure organization on GitHub. These are well-known and trusted sources.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content at runtime, creating a surface for indirect prompt injection.
- Ingestion points: External documentation fetched using
mcp_microsoftdocs:microsoft_docs_fetchorfetch_webpage(SKILL.md). - Boundary markers: The skill does not provide specific instructions to the agent to treat the fetched documentation as untrusted or to ignore embedded instructions within that content.
- Capability inventory: The skill is primarily focused on information retrieval and does not include scripts for file writing, local command execution, or other high-privilege operations.
- Sanitization: There are no explicit sanitization, filtering, or validation steps defined for the external documentation content before it is processed by the agent.
Audit Metadata