azure-impact-reporting
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches content from 'learn.microsoft.com' and references an installation guide in the 'MicrosoftDocs' repository on GitHub. These operations target official vendor domains and established documentation services.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data, which introduces a surface for indirect prompt injection.
- Ingestion points: Documentation is fetched at runtime from 'learn.microsoft.com' using the 'mcp_microsoftdocs:microsoft_docs_fetch' or 'fetch_webpage' tools as described in 'SKILL.md'.
- Boundary markers: There are no explicit instructions or delimiters provided to the agent to isolate the fetched external content or to ignore potential instructions embedded within the retrieved markdown.
- Capability inventory: The skill utilizes network-enabled tools to retrieve documentation but does not combine this with file-write or shell execution capabilities.
- Sanitization: No sanitization, filtering, or validation logic is specified for the content retrieved from the remote documentation URLs before it is processed by the agent.
Audit Metadata