azure-cosmos-db
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a comprehensive index of Azure Cosmos DB documentation. All external links point to trusted domains, including learn.microsoft.com and official Microsoft GitHub organizations.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch external data, which introduces a potential attack surface. However, the risk is negligible given the trusted nature of the sources and the lack of dangerous capabilities within the skill.\n
- Ingestion points: External content is fetched from learn.microsoft.com via the mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage tools as described in SKILL.md.\n
- Boundary markers: The skill instructions do not specify explicit delimiters or warnings for the fetched content.\n
- Capability inventory: Analysis of the skill files confirms there are no scripts, subprocess calls, file-write operations, or network-send operations present.\n
- Sanitization: No sanitization is performed by the skill itself, as it relies on the agent platform's tool implementation and the integrity of the official documentation sources.
Audit Metadata