azure-cosmos-java

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill documents the official Azure Cosmos DB Java SDK. All external links point to trusted domains, including Microsoft documentation (learn.microsoft.com), Azure SDK documentation (azuresdkdocs.z19.web.core.windows.net), and Maven Central (central.sonatype.com). These resources are recognized as well-known technology services.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface area for processing external data from a database, which could theoretically contain malicious instructions.
  • Ingestion points: The skill demonstrates reading data using container.readItem and container.queryItems in SKILL.md.
  • Boundary markers: No explicit boundary markers or instruction-ignoring warnings are present for database record contents.
  • Capability inventory: The skill does not define or utilize tools for shell command execution, file system modification, or arbitrary network requests beyond standard SDK communication with Azure services.
  • Sanitization: The skill proactively demonstrates security best practices by using SqlParameter for parameterized queries, which mitigates standard SQL injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 09:42 PM