azure-container-apps
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from learn.microsoft.com and provides links to the official MicrosoftDocs GitHub organization. These are trusted, well-known services associated with the skill author.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external content via specialized fetch tools, creating a theoretical surface for indirect prompt injection. However, since the sources are restricted to official vendor documentation, the risk is negligible.
- Ingestion points: Tools like mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage are used to retrieve documentation from the web into the agent's context.
- Boundary markers: The skill instructions do not specify the use of delimiters or boundary markers for the retrieved content.
- Capability inventory: The skill leverages read_file and network-based documentation retrieval tools.
- Sanitization: No specific sanitization or content filtering is defined for the fetched data.
Audit Metadata